浏览全部资源
扫码关注微信
收稿日期：2025-01-02，
修回日期：2025-02-23，
录用日期：2025-03-03，
网络出版日期：2025-03-25，
移动端阅览
目标检测是计算机视觉领域的核心任务，其通过深度神经网络技术识别图像中的视觉对象并预测其位置和类别。在闭集环境下，目标检测器已显著展现出实用价值；然而，在开放环境中，这些系统面临着诸多挑战，包括不断变化的数据分布、新类别的出现以及噪声干扰，均可能影响决策准确性。相较于闭集环境下的综述性研究，开放环境中的目标检测及其特有挑战的应对策略仍显不足。本文深入分析了开放环境下目标检测面临的主要挑战，包括域外和类别外数据的处理，以及如何通过鲁棒和增量学习适应环境动态。我们首次全面分析了现有检测方法如何应对这些挑战，总结了它们在适应新场景、提高决策鲁棒性、以及支持持续学习方面的方法。进一步地，本文探讨了改进目标检测系统的可能方向，包括开发能够处理更广泛数据集的新方法，整合领域知识增强决策的上下文依赖性，以及设计动态适应的攻防机制和新类别的学习算法。通过这项工作，我们希望为开放环境中的目标检测技术提供一种全新的、系统化的视角，以促进未来更加稳健的解决方案开发，并推动该技术在实际应用中的进一步发展。
Object detection is a fundamental task in computer vision， employing deep neural networks to identify and localize objects in images. Under closed-set conditions， where training and test data share similar distributions and the set of categories remains fixed， object detection systems have achieved remarkable success. These systems now play a pivotal role in applications such as autonomous driving， medical imaging， and facial recognition. However， the shift from closed-set to open-environment scenarios introduces complex challenges， reflecting the unpredictability and diversity of real-world conditions. These include changes in data distribution （domain shift）， the emergence of new categories， and the presence of noise， all of which significantly impact the robustness and accuracy of object detection models. Furthermore， the integration of object detection systems into real-world applications often necessitates balancing performance with resource efficiency， posing additional challenges in achieving scalability， interpretability， and low-latency processing for time-critical scenarios like video analytics and disaster response systems.This paper systematically investigates the challenges of object detection in open environments， focusing on four key areas： handling out-of-distribution （OOD） data， detecting objects in unknown categories， improving model robustness， and enabling incremental learning. First， addressing OOD challenges requires robust domain adaptation and domain generalization methods. The inability of traditional object detectors to generalize beyond their training domain often leads to degraded performance when deployed in diverse real-world settings. Techniques such as intermediate domain generation， adversarial learning， and contrastive learning have emerged as promising approaches to mitigate domain shift. These methods enhance generalization by enabling models to learn invariant features across domains or simulate unseen domains during training. Furthermore， unsupervised and semi-supervised learning paradigms extend these capabilities by leveraging unlabeled data to adapt detectors to new conditions.The second challenge pertains to detecting objects in unknown categories， a scenario common in real-world environments where new object categories may appear post-training. Traditional detectors， limited by their closed-set assumptions， struggle with this open-world requirement. Approaches addressing this issue include distinguishing known from unknown objects through uncertainty estimation and synthesizing pseudo-labels for unknown categories. Furthermore， leveraging auxiliary information such as attributes or visual-textual alignment enables detectors to infer relationships between known and unknown objects， improving their ability to identify and classify novel categories. Expanding these techniques to include cross-modal fusion strategies and leveraging contextual priors can further enhance performance in open-world scenarios.Robustness is the third critical focus area， particularly in defending against adversarial attacks and environmental noise. In open environments， object detection models must maintain reliability despite attempts to compromise their predictions through adversarial perturbations or natural disruptions such as occlusions or poor lighting. Techniques such as adversarial training， noise suppression modules， and the integration of domain-specific knowledge have shown promise in enhancing model resilience. The paper reviews advancements in both defense mechanisms and adaptive adversarial training frameworks that ensure robustness without compromising performance on clean data. The exploration of novel architectures， such as transformer-based detectors， also holds potential for building inherently robust systems capable of learning global and local context simultaneously.Incremental learning represents the fourth challenge， addressing the need for models to adapt continually to new tasks or categories without forgetting previously learned knowledge. Traditional training processes often overwrite prior knowledge when exposed to new data， a phenomenon known as catastrophic forgetting. Solutions to this issue include knowledge distillation， pseudo-labeling， and data replay strategies. These approaches allow detectors to balance learning new information while preserving performance on previously encountered tasks or categories. The integration of large-scale pre-trained models and generative techniques for creating synthetic data has further advanced the field by providing scalable and flexible solutions. Moreover， optimizing these methods to operate under constrained computational environments remains a key area for future research.This paper provides a comprehensive review of the methodologies and frameworks developed to tackle these challenges， assessing their strengths and limitations. Through detailed analysis， we identify key opportunities for advancing object detection technology in open environments. Future research directions include： （1） constructing diverse and comprehensive datasets that better reflect the complexity of real-world scenarios； （2） exploring the use of multi-modal inputs， such as combining visual data with textual descriptions， to enhance contextual understanding； （3） developing lightweight， real-time adaptive mechanisms to defend against adversarial attacks； and （4） optimizing incremental learning algorithms to reduce computational costs while preserving accuracy across tasks. Additionally， fostering collaboration between academia and industry is critical to address these challenges effectively， accelerating the translation of research breakthroughs into practical applications.By synthesizing insights from state-of-the-art methods and identifying critical gaps in current research， this work contributes a systematic perspective on the evolving landscape of object detection in open environments. This perspective aims to inspire innovative solutions that enhance the robustness， adaptability， and scalability of object detection systems. Ultimately， the advancements discussed here will empower object detection technologies to address the demands of dynamic real-world applications， fostering their adoption in diverse fields such as public safety， industrial automation， and healthcare， while paving the way for interdisciplinary innovations in robotics， augmented reality， and smart cities.
Alemi AA ， Fischer I ， Dillon JV and Murphy K . 2017 . Deep variational information bottleneck // the 5th International Conference on Learning Representations . Toulon， France ： arXiv： 1612 . 00410 ［ DOI： 10.48550/arXiv.1612.00410 http://dx.doi.org/10.48550/arXiv.1612.00410 ］
Bansal A ， Sikka K ， Sharma G ， Chellappa R and Divakaran A . 2018 . Zero-shot object detection // Proceedings of the European Conference on Computer Vision . Munich， Germany ： 384 - 400 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Bendale A and Boult T . 2015 . Towards open world recognition // InProceedings of the IEEE conference on computer vision and pattern recognition . Boston， USA ： IEEE： 1893 - 1902 ［ DOI： 10.1109/CVPR.2015.7298799 http://dx.doi.org/10.1109/CVPR.2015.7298799 ］
Bochkovskiy A ， Wang C Y ， and Liao H Y M . 2020 . Yolov4： Optimal speed and accuracy of object detection ［EB/OL］.［ 2024-09-20 ］. https://www.arxiv.org/pdf/2004.10934.pdf https://www.arxiv.org/pdf/2004.10934.pdf
Brooks T ， Holynski A ， and Efros A A . 2023 . Instructpix2pix： Learning to follow image editing instructions // Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Vancouver， Canada ： IEEE： 18392 - 18402 ［ DOI： 10.1109/CVPR52729.2023.01764 http://dx.doi.org/10.1109/CVPR52729.2023.01764 ］
Cao J ， Li Y L ， Sun H Q ， Xie J ， Huang K Q ， Pang Y W . 2022 . A survey on deep learning based visual object detection ， 27 （ 6 ）： 1697 - 1722
曹家乐 ， 李亚利 ， 孙汉卿 ， 谢今 ， 黄凯奇 ， 庞彦伟 . 2022 . 基于深度学习的视觉目标检测技术综述 . 中国图象图形学报 ， 27 （ 6 ）： 1697 - 1722 ［ DOI： 10.11834/jig.220069 http://dx.doi.org/10.11834/jig.220069 ］
Cao S C ， Joshi D ， Gui L Y and Wang Y X . 2023 . Contrastive Mean Teacher for Domain Adaptive Object Detectors // Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （2023） . Vancouver， Canada ： IEEE： 23839 - 23848 ［ DOI： 10.1109/CVPR52729.2023.02283 http://dx.doi.org/10.1109/CVPR52729.2023.02283 ］
Chen C Q ， Li J C ， Zheng Z B ， Huang Y ， Ding X H and Yu Y Z . 2021 . Dual bipartite graph learning： A general approach for domain adaptive object detection // Proceedings of 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . Montreal， Canada ： IEEE： 2703 - 2712 ［ DOI： 10.1109/ICCV48922.2021.00270 http://dx.doi.org/10.1109/ICCV48922.2021.00270 ］
Chen C Q ， Li J C ， Zhou H Y ， Han X G ， Huang Y ， Ding X H and Yu Y Z . 2022 . Relation matters： Foreground-aware graph-based relational reasoning for domain adaptive object detection . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 45 ： 3677 - 3694 ［ DOI： 10.1109/TPAMI.2022.3179445 http://dx.doi.org/10.1109/TPAMI.2022.3179445 ］
Chen C Q ， Zheng Z B ， Ding X H ， Huang Y and Dou Q . 2020 . Harmonizing transferability and discriminability for adapting object detectors // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Seattle， USA ： IEEE： 8869 - 8878 ［ DOI： 10.1109/CVPR42600.2020.00889 http://dx.doi.org/10.1109/CVPR42600.2020.00889 ］
Chen M L ， Chen W J ， Yang S C ， Song J ， Wang X C ， Zhang L ， Yan Y F ， Qi D L ， Zhuang Y T ， Xie D and Pu S L . 2022 . Learning Domain Adaptive Object Detection with Probabilistic Teacher // Proceedings of the International Conference on Machine Learning . PMLR ： 3040 - 3055 ［ DOI： 10.48550/arXiv.2206.06293 http://dx.doi.org/10.48550/arXiv.2206.06293 ］
Chen P C ， Kung B H and Chen J C . 2021 . Class-aware robust adversarial training for object detection // InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Virtual ： IEEE： 10420 - 10429 ［ DOI： 0.48550/arXiv.2103.16148 http://dx.doi.org/0.48550/arXiv.2103.16148 ］
Chen X ， Xie C ， Tan M ， Zhang L ， Hsieh C J and Gong B . 2021 . Robust and accurate object detection via adversarial learning // InProceedings of the IEEE/CVF conference on computer vision and pattern recognition . Nashville， TN， USA ： IEEE： 16622 - 16631 ［ DOI： 10.48550/arXiv.2103.13886 http://dx.doi.org/10.48550/arXiv.2103.13886 ］
Chen Y H ， Li W ， Sakaridis C ， Dai D X and Van Gool L . 2018 . Domain adaptive Faster R-CNN for object detection in the wild // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， Utah， USA ： IEEE： 3339 - 3348 ［ DOI： 10.1109/CVPR.2018.00352 http://dx.doi.org/10.1109/CVPR.2018.00352 ］
Chen Y ， Song P H ， Liu H ， Dai L H ， Zhang X C ， Ding R W and Li S Q . 2023 . Achieving domain generalization for underwater object detection by domain mixup and contrastive learning . Neurocomputing ， 528 ： 20 - 34 ［ DOI： 10.1016/j.neucom.2023.01.053 http://dx.doi.org/10.1016/j.neucom.2023.01.053 ］
Cheng J ， Huang B ， Fang Y ， Han Z and Wang Z . 2024 . Adversarial Intensity Awareness for Robust Object Detection . Computer Vision and Image Understanding ， 45 ： 3677 - 3694 ［ DOI： 10.2139/ssrn.4279328 http://dx.doi.org/10.2139/ssrn.4279328 ］
Cheng T ， Song L ， Ge Y ， Liu W ， Wang X and Shan Y . 2024 . YOLO-World： real-time open-vocabulary object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， WA， USA ： IEE： 16901 - 16911 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Chiang P H ， Chan C S and Wu S H . 2021 . Adversarial pixel masking： A defense against physical attacks for pre-trained object detectors // InProceedings of the 29th ACM international conference on multimedia . Chengdu， China ： IEEE： 1856 - 1865 ［ DOI： 10.1145/3474085.3475338 http://dx.doi.org/10.1145/3474085.3475338 ］
Chiang P Y ， Curry M ， Abdelkader A ， Kumar A ， Dickerson J and Goldstein T . 2020 . Detection as regression： Certified object detection with median smoothing // Advances in Neural Information Processing Systems . virtual ： IEEE： 1275 - 86 .［ DOI： 10.48550/arXiv.2007.03730 http://dx.doi.org/10.48550/arXiv.2007.03730 ］
Choi T M and Kim J H . 2023 . Incremental few-shot object detection via simple fine-tuning approach // In2023 IEEE International Conference on Robotics and Automation （ICRA） . London， England ： IEEE： 9289 - 9295 ［ DOI： 10.1109/ICRA48891.2023.10160283 http://dx.doi.org/10.1109/ICRA48891.2023.10160283 ］
Chu Q S ， Li S Y ， Chen G Y ， Li K ， and Li X . 2023 . Adversarial alignment for source free object detection // Proceedings of the 37th AAAI Conference on Artificial Intelligence . Washington， USA ： AAAI： 452 - 460 ［ DOI： 10.1609/aaai.v37i1.25119 http://dx.doi.org/10.1609/aaai.v37i1.25119 ］
Danish M S ， Khan M H ， Munir M A ， Sarfraz M S and Ali M . 2024 . Improving Single Domain-Generalized Object Detection： A Focus on Diversification and Alignment // Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Seattle WA， USA ： IEEE： 17732 - 17742 ［ DOI： 10.1109/CVPR52733.2024.01679 http://dx.doi.org/10.1109/CVPR52733.2024.01679 ］
Deng J H ， Li W ， Chen Y H and Duan L X . 2021 . Unbiased mean teacher for cross-domain object detection // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Nashville， USA ： IEEE： 4091 - 4101 ［ DOI： 10.1109/CVPR46437.2021.00408 http://dx.doi.org/10.1109/CVPR46437.2021.00408 ］
Deng Z W ， Kong Q ， Akira N and Yoshinaga T . 2022 . Hierarchical contrastive adaptation for cross-domain object detection . Machine Vision and Applications ， 33 ： 403 - 405 ［ DOI： 10.1007/s00138-022-01317-7 http://dx.doi.org/10.1007/s00138-022-01317-7 ］
Dong N ， Zhang Y ， Ding M and Lee G H . 2021 . Bridging non co-occurrence with unlabeled in-the-wild data for incremental object detection // Advances in Neural Information Processing Systems . Virtual-only ： ACM： 30492 - 503 .［ DOI： 10.48550/arXiv.2110.15017 http://dx.doi.org/10.48550/arXiv.2110.15017 ］
Dong Z ， Wei P and Lin L . 2022 . Adversarially-aware robust object detector // InEuropean Conference on Computer Vision . Switzerland ： Springer： 297 - 313 ［ DOI： 10.48550/arXiv.2207.06202 http://dx.doi.org/10.48550/arXiv.2207.06202 ］
Du X ， Wang X ， Gozum G and Li Y . 2022 . Unknown-aware object detection： Learning what you don't know from videos in the wild // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 13678 - 13688 ［ DOI： 10.48550/arXiv.2203.03800 http://dx.doi.org/10.48550/arXiv.2203.03800 ］
Du X ， Wang Z ， Cai M and Li Y . 2022 . VOS： learning what you don’t know by virtual outlier synthesis // the 10th International Conference on Learning Representations . Switzerland ： Springer： 297 - 313 ［ DOI： 10.48550/arXiv.2202.01197 http://dx.doi.org/10.48550/arXiv.2202.01197 ］
Du Y ， Wei F ， Zhang Z ， Shi M ， Gao Y and Li G . 2022 . Learning to prompt for open-vocabulary object detection with vision-language model // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 14084 - 14093 ［ DOI： 10.48550/arXiv.2203.14940 http://dx.doi.org/10.48550/arXiv.2203.14940 ］
Duan K ， Bai S ， Xie L ， Qi H ， Huang Q and Tian Q . 2019 . Centernet： Keypoint triplets for object detection // InProceedings of the IEEE/CVF international conference on computer vision . Seoul， Korea ： IEEE： 6569 - 6578 ［ DOI： 10.48550/arXiv.1904.08189 http://dx.doi.org/10.48550/arXiv.1904.08189 ］
Dziugaite G K ， Ghahramani Z and Roy D M . 2016 . A study of the effect of jpg compression on adversarial images ［EB/OL］. ［ 2016-08-02 ］. https://arxiv.org/abs/1608.00853 https://arxiv.org/abs/1608.00853
Feng C ， Zhong Y ， Jie Z ， Chu X ， Ren H ， Wei X ， Xie W and Ma L . 2022 . Promptdet： Towards open-vocabulary detection using uncurated images // European Conference on Computer Vision . Tel Aviv， Israel： 701 - 717 ［ DOI： 10.48550/arXiv.2203.16513 http://dx.doi.org/10.48550/arXiv.2203.16513 ］
Feng D ， Haase-Schütz C ， Rosenbaum L ， Hertlein H ， Glaeser C ， Timm F ， and Dietmayer K . 2020 . Deep multi-modal object detection and semantic segmentation for autonomous driving： Datasets， methods， and challenges . IEEE Transactions on Intelligent Transportation Systems ， 22 （ 3 ）： 1341 - 1360 ［ DOI： 10.1109/TITS.2020.2972974 http://dx.doi.org/10.1109/TITS.2020.2972974 ］
Feng T ， Wang M and Yuan H . 2022 . Overcoming catastrophic forgetting in incremental object detection via elastic response distillation // InProceedings of the IEEE/CVF conference on computer vision and pattern recognition . Vancouver， Canada ： IEEE： 9427 - 9436 ［ DOI： 10.48550/arXiv.2204.02136 http://dx.doi.org/10.48550/arXiv.2204.02136 ］
Ganin Y ， Ustinova E ， Ajakan H ， Germain P ， Larochelle H ， Laviolette F ， March M and Lempitsky V . 2016 . Domain-adversarial training of neural networks . Journal of Machine Learning Research ， 17 （ 59 ）： 1 - 35 ［ DOI： 10.1007/978-3-319-58347-1_10 http://dx.doi.org/10.1007/978-3-319-58347-1_10 ］
Gao M ， Xing C ， Niebles JC ， Li J ， Xu R ， Liu W and Xiong C . 2022 . Open vocabulary object detection with pseudo bounding-box labels // European Conference on Computer Vision . Tel Aviv， Israel： 266 - 282 ［ DOI： 10.48550/arXiv.2111.09452 http://dx.doi.org/10.48550/arXiv.2111.09452 ］
Girshick R . 2015 . Fast r-cnn // In Proceedings of the IEEE International Conference on Computer Vision . Santiago， Chile ： IEEE： 1440 – 1448 ［ DOI： 10.48550/arXiv.1504.08083 http://dx.doi.org/10.48550/arXiv.1504.08083 ］
Gu X ， Lin TY ， Kuo W and Cui Y . 2021 . Open-vocabulary object detection via vision and language knowledge distillation . ［EB/OL］. ［ 2021-04-28 ］. https://arxiv.org/abs/2104.13921 https://arxiv.org/abs/2104.13921
Guo Q ， Sun J Y ， Xu F ， Ma L ， Xie X F ， Feng W ， Liu Y and Zhao J J . 2021 . Efficientderain： Learning pixel-wise dilation filtering for high-efficiency single-image deraining // Proceedings of the 35th AAAI Conference on Artificial Intelligence . Vancouver， Canada ： AAAI： 1487 - 1495 ［ DOI： 10.1609/aaai.v35i2.16239 http://dx.doi.org/10.1609/aaai.v35i2.16239 ］
Gupta A ， Narayan S ， Joseph KJ ， Khan S ， Khan FS and Shah M . 2022 . Ow-detr： Open-world detection transformer // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 9235 - 9244 ［ DOI： 10.48550/arXiv.2112.01513 http://dx.doi.org/10.48550/arXiv.2112.01513 ］
Gupta A ， Narayan S ， Khan S ， Khan FS ， Shao L and Van De Weijer J . 2023 . Generative Multi-Label Zero-Shot Learning . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 45 （ 12 ）： 14611 - 14624 ［ DOI： 10.1109/TPAMI.2023.3295772 http://dx.doi.org/10.1109/TPAMI.2023.3295772 ］
Han H ， Hu X ， Hao Y ， Xu K ， Dang P ， Wang Y ， Zhao Y ， Du Z ， Guo Q ， Wang Y and Zhang X . 2023 . Real-time robust video object detection system against physical-world adversarial attacks . IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ， 43 （ 1 ）： 366 - 379 ［ DOI： 10.1109/TCAD.2023.3305932 http://dx.doi.org/10.1109/TCAD.2023.3305932 ］
Han J ， Ren Y ， Ding J ， Pan X ， Yan K and Xia GS . 2022 . Expanding low-density latent regions for open-set object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 9591 - 9600 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
He M Z ， Wang Y L ， Wu J X ， Wang Y R ， Li H Q ， Li B ， Gan W H ， Wu W ， and Qiao Y . 2022 . Cross domain object detection by target-perceived dual branch distillation // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . New Orleans， USA ： IEEE： 9570 - 9580 ［ DOI： 10.1109/CVPR52688.2022.00935 http://dx.doi.org/10.1109/CVPR52688.2022.00935 ］
He Z W and Zhang L . 2019 . Multi-adversarial Faster-RCNN for unrestricted object detection // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （2019） . Seoul， Korea ： IEEE： 6667 - 6676 ［ DOI： 10.1109/ICCV.2019.00677 http://dx.doi.org/10.1109/ICCV.2019.00677 ］
He Z W and Zhang L . 2020 . Domain adaptive object detection via asymmetric tri-way faster-rcnn // Proceedings of the 16th European Conference on Computer Vision . Glasgow ： Springer： 309 - 324 ［ DOI： 10.1007/978-3-030-58586-0_19 http://dx.doi.org/10.1007/978-3-030-58586-0_19 ］
Ho J ， Jain A and Abbeel P . 2020 . Denoising diffusion probabilistic models // Proceedings of the 34th Neural Information Processing Systems . Vancouver， Canada ： NeurIPS： 6840 - 6851 ［ DOI： 10.48550/arXiv.2006.11239 http://dx.doi.org/10.48550/arXiv.2006.11239 ］
Hosla P ， Teterwak P ， Wang C ， Sarna A ， Tian Y L ， Isola P ， Maschinot A ， Liu C and Krishnan D . 2020 . Supervised contrastive learning // Proceedings of the 34th Conference on Neural Information Processing Systems . Vancouver， Canada ： NeurIPS： 18661 - 18673 ［ DOI： 10.48550/arXiv.2004.11362 http://dx.doi.org/10.48550/arXiv.2004.11362 ］
Hsu H K ， Yao C H ， Tsai Y H ， Hung W C ， Tseng H Y ， Singh M and Yang M H . 2020 . Progressive domain adaptation for object detection // Proceedings of 2020 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . Snowmass Village， CO， USA ： IEEE： 749 - 757 ［ DOI： 10.1109/WACV45572.2020.9093358 http://dx.doi.org/10.1109/WACV45572.2020.9093358 ］
Huang J X ， Guan D Y ， Xiao A R and Lu S J . 2021 . Model adaptation： Historical contrastive learning for unsupervised domain adaptation without source data // Proceedings of the 35th Neural Information Processing Systems . Vancouver， Canada ： NeurIPS： 3635 - 3649 ［ DOI： 10.48550/arXiv.2110.03374 http://dx.doi.org/10.48550/arXiv.2110.03374 ］
Huang P ， Han J ， Cheng D and Zhang D . 2022 . Robust region feature synthesizer for zero-shot object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 7622 - 7631 ［ DOI： 10.48550/arXiv.2201.0010 http://dx.doi.org/10.48550/arXiv.2201.0010 ］
Huang T ， Huang C C ， Ku C H and Chen J C . 2024 . Blenda： Domain Adaptive Object Detection Through Diffusion-Based Blending // ICASSP 2024-2024 IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP） . Seoul， Korea ： IEEE： 4075 - 4079 ［ DOI： 10.1109/ICASSP48485.2024.10446537 http://dx.doi.org/10.1109/ICASSP48485.2024.10446537 ］
Huang W J ， Lu Y L ， Lin S Y ， Xie Y S and Lin Y Y . 2022 . AQT： Adversarial query transformers for domain adaptive object detection // Proceedings of the 31th International Joint Conference on Artificial Intelligence . Messe Wien， Vienna， Austria ： IJCAI： 972 - 979 ［ DOI： 10.24963/ijcai.2022/136 http://dx.doi.org/10.24963/ijcai.2022/136 ］
Im Choi J and Tian Q . 2022 . Adversarial attack and defense of yolo detectors in autonomous driving scenarios // In2022 IEEE Intelligent Vehicles Symposium （IV） . Aachen， Germany ： IEEE： 1011 - 1017 ［ DOI： 10.48550/arXiv.2202.04781 http://dx.doi.org/10.48550/arXiv.2202.04781 ］
Inoue N ， Furuta R ， Yamasaki T and Aizawa K . 2018 . Cross-domain weakly-supervised object detection through progressive domain adaptation // Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition （CVPR） . Salt Lake City， Utah， USA ： IEEE： 5001 - 5009 ［ DOI： 10.1109/CVPR.2018.00525 http://dx.doi.org/10.1109/CVPR.2018.00525 ］
Jeon M ， Seo J and Min J . 2023 . DA-RAW： Domain Adaptive Object Detection for Real-World Adverse Weather Conditions // Proceedings of the 2024 IEEE International Conference on Robotics and Automation . Yokohama， Japan ： IEEE： 2013 - 2020 ［ DOI： 10.1109/ICRA57147.2024.10611219 http://dx.doi.org/10.1109/ICRA57147.2024.10611219 ］
Jiang H and Learned-Miller E . 2017 . Face detection with the faster R-CNN // In2017 12th IEEE international conference on automatic face & gesture recognition . Washington， USA ： IEEE： 650 - 657 ［ DOI： 10.1109/FG.2017.82 http://dx.doi.org/10.1109/FG.2017.82 ］
Jing L ， Wang R ， Ren W ， Dong X and Zou C . 2024 . PAD： Patch-Agnostic Defense against Adversarial Patch Attacks // In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA： 24472 - 24481 ［ DOI： 10.48550/arXiv.2404.16452 http://dx.doi.org/10.48550/arXiv.2404.16452 ］
Joseph K J ， Khan S ， Khan F S and Balasubramanian V N . 2021 . Towards open world object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， TN， USA ： 5830 - 5840 ［ DOI： 10.48550/arXiv.2103.02603 http://dx.doi.org/10.48550/arXiv.2103.02603 ］
Joseph K J ， Rajasegaran J ， Khan S ， Khan F S and Balasubramanian V N . 2022 . Incremental object detection via meta-Learning . in IEEE Transactions on Pattern Analysis and Machine Intelligence ， 44 （ 12 ）： 9209 - 9216 ［ DOI： 10.1109/TPAMI.2021.3124133 http://dx.doi.org/10.1109/TPAMI.2021.3124133 ］
Kang M ， Zhang J ， Zhang J ， Wang X ， Chen Y ， Ma Z and Huang X . 2023 . Alleviating catastrophic forgetting of incremental object detection via within-class and between-class knowledge distillation // In Proceedings of the IEEE/CVF International Conference on Computer Vision . Paris， France ： IEEE： 18894 – 18904 ［ DOI： 10.1109/ICCV51070.2023.01732 http://dx.doi.org/10.1109/ICCV51070.2023.01732 ］
Kennerley M ， Wang J G ， Veeravalli B and Tan R T . 2024 . CAT： Exploiting inter-class dynamics for domain adaptive object detection // Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Seattle WA， USA ： IEEE： 16541 - 16550 ［ DOI： 10.1109/CVPR52733.2024.01565 http://dx.doi.org/10.1109/CVPR52733.2024.01565 ］
Khanh T L B ， Nguyen H H ， Pham L H ， Tran D N N and Jeon J W . 2024 . Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection ［EB/OL］.［ 2024-09-20 ］. https://www.arxiv.org/pdf/2407.16497.pdf https://www.arxiv.org/pdf/2407.16497.pdf
Khodabandeh M ， Vahdat A ， Ranjbar M and Macready W G . 2019 . A robust learning approach to domain adaptive object detection. Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV） . Long Beach， CA， USA ： IEEE ： 480 - 490 ［ DOI： 10.1109/ICCV.2019.00057 http://dx.doi.org/10.1109/ICCV.2019.00057 ］
Kim D ， Angelova A and Kuo W . 2023 . Region-aware pretraining for open-vocabulary object detection with vision transformers // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver， BC， Canada ： 11144 - 11154 ［ DOI： 10.48550/arXiv.2305.07011 http://dx.doi.org/10.48550/arXiv.2305.07011 ］
Kim J ， Cho E ， Kim S and Kim H J . 2024 . Retrieval-augmented open-vocabulary object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， WA， USA ： 17427 - 17436 ［ DOI： 10.48550/arXiv.2404.05687 http://dx.doi.org/10.48550/arXiv.2404.05687 ］
Kim J ， Cho H ， Kim J ， Tiruneh Y Y and Baek S . 2024 . Sddgr： Stable diffusion-based deep generative replay for class incremental object detection // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 28772 – 28781 ［ DOI： 10.48550/arXiv.2402.17323 http://dx.doi.org/10.48550/arXiv.2402.17323 ］
Kim T ， Jeong M ， Kim S ， Choi S and Kim C . 2019 . Diversify and match： A domain adaptive representation learning paradigm for object detection // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Long Beach， CA， USA ： IEEE： 12456 - 12465 ［ DOI： 10.1109/CVPR.2019.01274 http://dx.doi.org/10.1109/CVPR.2019.01274 ］
Kirkpatrick J ， Pascanu R ， Rabinowitz N ， Veness J ， Desjardins G ， Rusu AA ， Milan K ， Quan J ， Ramalho T ， Grabska-Barwinska A and Hassabis D . 2017 . Overcoming catastrophic forgetting in neural networks // Proceedings of the National Academy of Sciences . Washington， USA ： IEEE： 3521 – 3526 ［ DOI： 10.1073/pnas.1611835114 http://dx.doi.org/10.1073/pnas.1611835114 ］
Kuo W ， Cui Y ， Gu X ， Piergiovanni AJ and Angelova A . 2022 . F-vlm： Open-vocabulary object detection upon frozen vision and language models ［EB/OL］. ［ 2022-05-21 ］. https://arxiv.org/pdf/2209.15639.pdf https://arxiv.org/pdf/2209.15639.pdf
Li D ， Tasci S ， Ghosh S ， Zhu J ， Zhang J and Heck L . 2019 . Rilod： Near real-time incremental learning for object detection at the edge // In Proceedings of the ACM/IEEE Symposium on Edge Computing . Washington， USA ： IEEE： 113 – 126 ［ DOI： 10.48550/arXiv.1904.00781 http://dx.doi.org/10.48550/arXiv.1904.00781 ］
Li H ， Feng C M ， Xu Y ， Zhou T ， Yao L ， Chang X 2023 . Zero-shot camouflaged object detection. IEEE Transactions on Image Processing . IEEE Transactions on Image Processing ， 32 ： 5126 - 5137 ［ DOI： 10.1109/TIP.2023.3308295 http://dx.doi.org/10.1109/TIP.2023.3308295 ］
Li J L ， Xu R S ， Ma J ， Zou Q ， Ma J Q and Yu H K . 2023 . Domain adaptive object detection for autonomous driving under foggy weather // Proceedings of 2023 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . Waikoloa， Hawaii ： IEEE： 612 - 622 ［ DOI： 10.1109/WACV56688.2023.00068 http://dx.doi.org/10.1109/WACV56688.2023.00068 ］
Li J ， Zhang J ， Li J ， Li G ， Liu S ， Lin L and Li G . 2024 . Learning background prompts to discover implicit knowledge for open vocabulary object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， WA， USA ： 16678 - 16687 ［ DOI： 10.48550/arXiv.2406.00510 http://dx.doi.org/10.48550/arXiv.2406.00510 ］
Li L H ， Zhang P ， Zhang H ， Yang J ， Li C ， Zhong Y ， Wang L ， Yuan L ， Zhang L ， Hwang J N and Chang K W . 2022 . Grounded language-image pre-training // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， USA ： 10965 - 10975 ［ DOI： 10.48550/arXiv.2112.03857 http://dx.doi.org/10.48550/arXiv.2112.03857 ］
Li S F ， Ye M ， Zhu X T ， Zhou L H and Xiong L . 2022 . Source-free object detection by learning to overlook domain style // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . （CVPR） . New Orleans， USA ： IEEE： 8014 - 8023 ［ DOI： 10.1109/CVPR52688.2022.00785 http://dx.doi.org/10.1109/CVPR52688.2022.00785 ］
Li W Y ， Liu X Y and Yuan Y X . 2022 . SIGMA： Semantic-complete graph matching for domain adaptive object detection // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . New Orleans， USA ： IEEE： 5291 - 5300 ［ DOI： 10.1109/CVPR52688.2022.00522 http://dx.doi.org/10.1109/CVPR52688.2022.00522 ］
Li X F ， Chen W J ， Xie D ， Yang S C ， Yuan P ， Pu S L ， and Zhuang Y T . 2021 . A free lunch for unsupervised domain adaptive object detection without source data // Proceedings of the AAAI Conference on Artificial Intelligence ， 35 （ 10 ）： 8474 - 8481 ［ DOI： 10.1609/aaai.v35i10.17029 http://dx.doi.org/10.1609/aaai.v35i10.17029 ］
Li X ， Chen H and Hu X . 2023 . On the importance of backbone to the adversarial robustness of object detectors ［EB/OL］. ［ 2023-05-27 ］. https://arxiv.org/abs/2305.17438 https://arxiv.org/abs/2305.17438
Li Y J ， Dai X L ， Ma C Y ， Liu Y C ， Chen K ， Wu B C ， He Z J ， Kitani K and Vajda P . 2022 . Cross-domain adaptive teacher for object detection // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . New Orleans， USA ： IEEE： 7581 - 7590 ［ DOI： 10.1109/CVPR52688.2022.00743 http://dx.doi.org/10.1109/CVPR52688.2022.00743 ］
Li Z Y ， Zhao L ， Chen W J ， Yang S C ， Xie D ， and Pu S L . 2022 . Target-aware auto-augmentation for unsupervised domain adaptive object detection // ICASSP 2022-2022 IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP） . Singapore ： IEEE： 3848 - 3852 ［ DOI： 10.1109/ICASSP43922.2022.9747711 http://dx.doi.org/10.1109/ICASSP43922.2022.9747711 ］
Li Z ， Yao L ， Zhang X ， Wang X ， Kanhere S and Zhang H . 2019 . Zero-shot object detection with textual descriptions // Proceedings of the AAAI Conference on Artificial Intelligence . Honolulu， Hawaii， USA ： 8690 - 8697 ［ DOI： 10.1609/aaai.v33i01.33018690 http://dx.doi.org/10.1609/aaai.v33i01.33018690 ］
Lin Z ， Wang Y and Tang Z . 2024 ， Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts // Proceedings of the NeurIPS . WA， USA： 16678 - 16687 ［ DOI： 10.48550/arXiv.2410.05963 http://dx.doi.org/10.48550/arXiv.2410.05963 ］
Linting Guan ， Yan Wu ， Junqiao Zhao ， and Chen Ye . 2018 . Learn to detect objects incrementally // In IEEE Intelligent Vehicles Symposium . Suzhou， China ： IEEE： 403 – 408 ［ DOI： 10.1109/IVS.2018.8500673 http://dx.doi.org/10.1109/IVS.2018.8500673 ］
Liu F ， Zhang X S ， Wan F ， Ji X Y and Ye Q X . 2021 . Domain contrast for domain adaptive object detection . IEEE Transactions on Circuits and Systems for Video Technology ， 32 （ 12 ）： 8227 - 8237 ［ DOI： 10.1109/TCSVT.2021.3091620 http://dx.doi.org/10.1109/TCSVT.2021.3091620 ］
Liu J ， Levine A ， Lau CP ， Chellappa R and Feizi S . 2022 . Segment and complete： Defending object detectors against adversarial patch attacks with robust patch detection // InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . LA， USA ： IEEE： 14973 - 14982 ［ DOI： 10.48550/arXiv.2112.04532 http://dx.doi.org/10.48550/arXiv.2112.04532 ］
Liu J ， Wen X ， Zhao S ， Chen Y and Qi X . 2024 . Can OOD Object Detectors Learn from Foundation Models？ // Proceedings of the ECCV . Milan， Italy ： IEEE： 3848 - 3852 ［ DOI： 10.1007/978-3-031-73254-6_13 http://dx.doi.org/10.1007/978-3-031-73254-6_13 ］
Liu L ， Kuang Z ， Chen Y ， Xue J H ， Yang W and Zhang W . 2020 . Incdet： in defense of elastic weight consolidation for incremental object detection . IEEE Transactions on Neural Networks and Learning Systems ， 32 （ 6 ）： 2306 - 19 ［ DOI： 10.1109/TNNLS.2020.3002583 http://dx.doi.org/10.1109/TNNLS.2020.3002583 ］
Liu X ， Yang H and Ravichandran A . 2020 . Multi-task incremental learning for object detection ［EB/OL］. ［ 2020-02-13 ］. https://arxiv.org/abs/2002.05347 https://arxiv.org/abs/2002.05347
Liu Y B ， Wang J H ， Huang C ， Wang Y W and Xu Y . 2023 . CIGAR： Cross-modality graph reasoning for domain adaptive object detection // Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Vancouver， Canada ： IEEE： 23776 - 23786 ［ DOI： 10.1109/CVPR52729.2023.02277 http://dx.doi.org/10.1109/CVPR52729.2023.02277 ］
Liu Y ， Cong Y ， Goswami D ， Liu X and van de Weijer J . 2023 . Augmented box replay： Overcoming foreground shift for incremental object detection // In Proceedings of the IEEE/CVF International Conference on Computer Vision . Paris， France ： IEEE： 11367 – 11377 ［ DOI： 10.1109/TNNLS.2020.3002583 http://dx.doi.org/10.1109/TNNLS.2020.3002583 ］
Liu Y C ， Ma C Y ， Dai X ， Tian J ， Vajda P ， He Z a nd Kira Z . 2022 . Open-set semi-supervised object detection // European Conference on Computer Vision . Tel Aviv， Israel： 143 - 159 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Ma S ， Wang Y ， Wei Y ， Fan J ， Li TH ， Liu H and Lv F . 2023 . Cat： Localization and identification cascade detection transformer for open-world object detection // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Vancouver， Canada ： IEEE： 19681 – 19690 ［ DOI： 10.1109/CVPR52688.2022.00522 http://dx.doi.org/10.1109/CVPR52688.2022.00522 ］
Ma Z ， Luo G ， Gao J ， Li L ， Chen Y ， Wang S ， Zhang C and Hu W . 2022 . Open-vocabulary one-stage detection with hierarchical visual-language knowledge distillation // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 14074 - 14083 ［ DOI： 10.1109/CVPR51538.2022.00526 http://dx.doi.org/10.1109/CVPR51538.2022.00526 ］
Mao Q ， Wang C ， Yu S ， Zheng Y and Li Y . 2020 . Zero-shot object detection with attributes-based category similarity . IEEE Transactions on Circuits and Systems II ： Express Briefs ， 67 （ 5 ）： 921 - 925 ［ DOI： 10.1109/TCSII.2020.2982316 http://dx.doi.org/10.1109/TCSII.2020.2982316 ］
Mattolin G ， Zanella L ， Ricci E and Wang Y M . 2023 . Confmix： Unsupervised domain adaptation for object detection via confidence-based mixing // Proceedings of 2023 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . Waikoloa， Hawaii ： IEEE： 423 - 433 ［ DOI： 10.1109/WACV56688.2023.00050 http://dx.doi.org/10.1109/WACV56688.2023.00050 ］
Menezes A G ， de Moura G ， Alves C and de Carvalho A C . 2023 . Continual object detection： a review of definitions， strategies， and challenges. Neural Networks， 161 （c） ： 476 – 493 ［ DOI： 10.1016/j.neunet.2023.01.041 http://dx.doi.org/10.1016/j.neunet.2023.01.041 ］
Miller D ， Dayoub F ， Milford M and Sünderhauf N . 2019 . Evaluating merging strategies for sampling-based uncertainty techniques in object detection // 2019 IEEE International Conference on Robotics and Automation . Montreal， QC， Canada ： 2348 - 2354 ［ DOI： 10.1109/TCSII.2020.2982316 http://dx.doi.org/10.1109/TCSII.2020.2982316 ］
Miller D ， Nicholson L ， Dayoub F and Sünderhauf N . 2018 . Dropout sampling for robust object detection in open-set conditions // 2018 IEEE International Conference on Robotics and Automation . Brisbane， QLD， Australia： 3243 - 3249 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Munir M A ， Khan M H ， Sarfraz M S and Ali M . 2023 . Domain adaptive object detection via balancing between self-training and adversarial learning . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 45 ： 14353 - 14365 ［ DOI： 10.1109/TPAMI.2023.3290135 http://dx.doi.org/10.1109/TPAMI.2023.3290135 ］
Naseer M ， Khan S and Porikli F . 2019 . Local gradients smoothing： Defense against localized adversarial attacks // In2019 IEEE Winter Conference on Applications of Computer Vision （WACV） . Waikoloa Village， HI， USA ： IEEE： 1300 - 1307 ［ DOI： 10.1145/3665892 http://dx.doi.org/10.1145/3665892 ］
Nie H ， Wang R and Chen X . 2022 . From node to graph： Joint reasoning on visual-semantic relational graph for zero-shot detection // Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision . Waikoloa， HI ： 1109 - 1118 ［ DOI： 10.1038/s42256-022-00568-3 http://dx.doi.org/10.1038/s42256-022-00568-3 ］
Oord A V D ， Li Y and Vinyals O . 2018 . Representation learning with contrastive predictive coding ［EB/OL］.［ 2024-09-20 ］. https://www.arxiv.org/pdf/1807.03748.pdf https://www.arxiv.org/pdf/1807.03748.pdf
Peng C ， Zhao K and Lovell B C . 2021， Faster ilod： incremental learning for object detectors based on faster rcnn . Pattern Recognition Letters ， 140 ： 109 – 115 ［ DOI： 10.1016/j.patrec.2020.09.030 http://dx.doi.org/10.1016/j.patrec.2020.09.030 ］
Peng C ， Zhao K ， Maksoud S ， Li M and Lovell B C . 2021 . Sid： incremental learning for anchor-free object detection via selective and inter related distillation . Computer vision and image understanding ， 210 ： 103229 ［ DOI： 10.1016/j.cviu.2021.103229 http://dx.doi.org/10.1016/j.cviu.2021.103229 ］
Perez-Rua J M ， Zhu X ， Hospedales T M ， Xiang T . 2020 . Incremental few-shot object detection // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Seattle， WA， USA ： IEEE： 13846 – 13855 ［ DOI： 10.1109/CVPR52688.2022.00522 http://dx.doi.org/10.1109/CVPR52688.2022.00522 ］
Radford A ， Kim J W ， Hallacy C ， Ramesh A ， Goh G ， Agarwal S ， Sastry G ， Askell A ， Mishkin P ， Clark J ， Krueger G and Sutskever I . 2021 . Learning transferable visual models from natural language supervision // Proceedings of the 38th International Conference on Machine Learning . Seattle， WA， USA ： PMLR： 8748 - 8763 ［ DOI： 10.1109/PMLR52688.2022.00522 http://dx.doi.org/10.1109/PMLR52688.2022.00522 ］
Radford A ， Kim JW ， Hallacy C ， Ramesh A ， Goh G ， Agarwal S ， Sastry G ， Askell A ， Mishkin P ， Clark J and Krueger G . 2021 . Learning transferable visual models from natural language supervision // Proceedings of the 38th International Conference on Machine Learning . Graz， Austria ： 8748 - 8763 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Rahman S ， Khan S and Barnes N . 2022 . Polarity loss： Improving visual-semantic alignment for zero-shot detection. IEEE Transactions on Neural Networks and Learning Systems . Seattle， WA， USA ： 1 - 13 ［ DOI： 10.1109/TNNLS.2022.3184821 http://dx.doi.org/10.1109/TNNLS.2022.3184821 ］
Ramakrishnan K ， Panda R ， Fan Q ， Henning J ， Oliva A and Feris R . 2020 . Relationship matters： Relation guided knowledge transfer for incremental learning of object detectors // In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Seattle， WA， USA ： IEEE： 250 – 251 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Ren S . 2016 . Faster r-cnn： Towards real-time object detection with region proposal networks // IEEE Transactions on Pattern Analysis and Machine Intelligence ， IEEE ： 1137 – 1149 ［ DOI： 10.1109/TPAMI.2016.2577031 http://dx.doi.org/10.1109/TPAMI.2016.2577031 ］
Rezaeianaran F ， Shetty R ， Aljundi R ， Olmeda Reino D ， Zhang S S and Schiele B . 2021 . Seeking Similarities over Differences： Similarity-based Domain Alignment for Adaptive Object Detection // Proceedings of 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . Nashville， USA ： IEEE： 9184 - 9193 ［ DOI： 10.1109/ICCV48922.2021.00907 http://dx.doi.org/10.1109/ICCV48922.2021.00907 ］
Rodriguez A L and Mikolajczyk K . 2019 . Domain adaptation for object detection via style consistency ［EB/OL］.［ 2024-09-20 ］. https://www.arxiv.org/pdf/1911.10033.pdf https://www.arxiv.org/pdf/1911.10033.pdf
Ross TY and Dollár GK . 2017 . Focal loss for dense object detection // In Proceedings of the IEEE International Conference on Computer Vision . Paris， France ： IEEE： 2980 – 2988 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Rossolini G ， Nesti F ， Brau F ， Biondi A and Buttazzo G . 2023 . Defending from physically-realizable adversarial attacks through internal over-activation analysis // InProceedings of the AAAI Conference on Artificial Intelligence . Washington DC， USA ： AAAI： 15064 - 15072 ［ DOI： 10.1038/s42256-022-00568-3 http://dx.doi.org/10.1038/s42256-022-00568-3 ］
Saito K ， Ushiku Y ， Harada T and Saenko K . 2019 . Strong-weak distribution alignment for adaptive object detection // Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Long Beach， CA， USA ： IEEE： 6949 - 6958 ［ DOI： 10.1109/CVPR.2019.00712 http://dx.doi.org/10.1109/CVPR.2019.00712 ］
Shi C J ， Zheng Y F and Chen Z D . 2024 . Domain adaptive thermal object detection with unbiased granularity alignment . ACM Transactions on Multimedia Computing， Communications， and Applications ： ACM ， 46 （ 8 ）： 5362 - 5383 ［ DOI： 10.1145/3665892 http://dx.doi.org/10.1145/3665892 ］
Shi H ， Hayat M ， Wu Y and Cai J . 2022 . Proposalclip： Unsupervised open-category object proposal generation via exploiting clip cues // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 9611 - 9620 ［ DOI： 10.1145/32918904 http://dx.doi.org/10.1145/32918904 ］
Shmelkov K ， Schmid C and Alahari K . 2017 . Incremental learning of object detectors without catastrophic forgetting // In Proceedings of the IEEE International Conference on Computer Vision . Venice， Italy ： IEEE： 3400 – 3409 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Su B ， Zhang H and Zhou Z . 2023 . Hsic-based moving weight averaging for few-shot open-set object detection // Proceedings of the 31st ACM International Conference on Multimedia . Ottawa ON Canada ： 5358 - 5369 ［ DOI： 10.48550/arXiv.2401.17238 http://dx.doi.org/10.48550/arXiv.2401.17238 ］
Tarvainen A and Valpola H . 2017 . Mean teachers are better role models： Weight-averaged consistency targets improve semi-supervised deep learning results // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， CA， USA ： 1195 - 1204 ［ DOI： 10.48550/arXiv.2421.17234 http://dx.doi.org/10.48550/arXiv.2421.17234 ］
Tian K ， Zhang C H ， Wang Y ， Xiang S M and Pan C H . 2021 . Knowledge mining and transferring for domain adaptive object detection // Proceedings of 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . Montreal， Canada ： IEEE： 9133 - 9142 ［ DOI： 10.1109/ICCV48922.2021.00900 http://dx.doi.org/10.1109/ICCV48922.2021.00900 ］
Van de Ven G M ， Tuytelaars T and Tolias AS . 2022 . Three types of incremental learning . Nature Machine Intelligence ， 4 （ 12 ）： 1185 – 1197 ［ DOI： 10.1038/s42256-022-00568-3 http://dx.doi.org/10.1038/s42256-022-00568-3 ］
Vibashan V ， Oza P ， Sindagi V A and Patel V M . 2022 . Mixture of Teacher Experts for Source-Free Domain Adaptive Object Detection // Proceedings of the 2022 IEEE International Conference on Image Processing （ICIP） . Bordeaux， France ： IEEE： 3606 - 3610 ［ DOI： 10.1109/ICIP46576.2022.9897795 http://dx.doi.org/10.1109/ICIP46576.2022.9897795 ］
Vidit V ， Engilberge M and Salzmann M . 2023 . Clip the gap： A single domain generalization approach for object detection // Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Vancouver， Canada ： IEEE： 3219 - 3229 ［ DOI： 10.1109/CVPR52729.2023.00314 http://dx.doi.org/10.1109/CVPR52729.2023.00314 ］
VS V ， Oza P ， and Patel V M . 2023 . Instance relation graph guided source-free domain adaptive object detection // Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Vancouver， Canada ： IEEE： 3520 - 3530 ［ DOI： 10.1109/CVPR52729.2023.00343 http://dx.doi.org/10.1109/CVPR52729.2023.00343 ］
Wang H S ， Liao S C ， and Shao L . 2021 . Afan： Augmented feature alignment network for cross-domain object detection . IEEE Transactions on Image Processing ， 30 ： 4046 - 4056 ［ DOI： 10.1109/TIP.2021.3066046 http://dx.doi.org/10.1109/TIP.2021.3066046 ］
Wang L ， Zhang X ， Su H and Zhu J . 2024 . A comprehensive survey of continual learning： theory， method and application . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 46 （ 8 ）： 5362 - 5383 ［ DOI： 10.1109/TPAMI.2024.3367329 http://dx.doi.org/10.1109/TPAMI.2024.3367329 ］
Wang Z ， Li Y ， Chen X ， Lim SN ， Torralba A ， Zhao H and Wang S . 2023 . Detecting everything in the open world： Towards universal object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver， BC， Canada ： 11433 - 11443 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Wong E ， Rice L ， Kolter JZ . 2020 . Fast is better than free： Revisiting adversarial training ［EB/OL］. ［ 2020-01-12 ］. https://arxiv.org/abs/2001.03994 https://arxiv.org/abs/2001.03994
Wu A and Deng C . 2024 . Modulated phase diffusor： content-oriented feature synthesis for detecting unknown objects // the 12th International Conference on Learning Representations . Vienna， Austria ： 142 - 144 ［ DOI： 10.48550/arXiv.2411.15328 http://dx.doi.org/10.48550/arXiv.2411.15328 ］
Wu A M and Deng C . 2022 . Single-domain generalized object detection in urban scene via cyclic-disentangled self-distillation // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . New Orleans， USA ： IEEE： 837 - 846 ［ DOI： 10.1109/CVPR52688.2022.00092 http://dx.doi.org/10.1109/CVPR52688.2022.00092 ］
Wu A ， Deng C and Liu W . Unsupervised out-of-distribution object detection via pca-driven dynamic prototype enhancement . IEEE Transactions on Image Processing ， 33 ： 2431 - 2446 ［ DOI： 10.1109/TIP.2024.3378464 http://dx.doi.org/10.1109/TIP.2024.3378464 ］
Wu B ， Chen J ， Cai D ， He X and Gu Q . 2021 . Do wider neural networks really help adversarial robustness？ // Advances in Neural Information Processing Systems . Virtual-only： 7054 - 67 ［ DOI： 10.48550/arXiv.2401.13285 http://dx.doi.org/10.48550/arXiv.2401.13285 ］
Wu B， Gu J， Li Z， Cai D， He X and Liu W. 2022 Towards efficient adversarial training on vision transformers//InEuropean Conference on Computer Vision . Switzerland ： Springer： 307 - 325 ［ DOI： 10.48550/arXiv.2401.18295 http://dx.doi.org/10.48550/arXiv.2401.18295 ］
Wu S ， Wang J ， Zhao J ， Wang Y and Liu X . 2024 . NAPGuard： Towards Detecting Naturalistic Adversarial Patches // In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA： 24367 - 24376 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Wu X ， Zhu F ， Zhao R and Li H . 2023 . Cora： Adapting clip for open-vocabulary detection with region prompting and anchor pre-matching // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver， BC， Canada ： 7031 - 7040 ［ DOI： 10.48550/arXiv.3219.38981 http://dx.doi.org/10.48550/arXiv.3219.38981 ］
Wu Z ， Lu Y ， Chen X ， Wu Z ， Kang L and Yu J . 2022 . UC-OWOD： Unknown-classified open world object detection // European Conference on Computer Vision . Tel Aviv， Israel： 193 - 210 ［ DOI： 10.48550/arXiv.3982.32189 http://dx.doi.org/10.48550/arXiv.3982.32189 ］
Xiang C and Mittal P . 2021 . Detectorguard ： Pr ovably securing object detectors against localized patch hiding attacks// InProceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security Vitural ： IEEE： 3177 - 3196 ［ DOI： 10.48550/arXiv.2401.17270 http://dx.doi.org/10.48550/arXiv.2401.17270 ］
Xie C ， Tan M ， Gong B ， Wang J ， Yuille AL and Le QV . 2020 . Adversarial examples improve image recognition // InProceedings of the IEEE/CVF conference on computer vision and pattern recognition . Washington， USA ： IEEE： 819 - 828 ［ DOI： 10.48550/arXiv.2401.85719 http://dx.doi.org/10.48550/arXiv.2401.85719 ］
Xiong L ， Ye M ， Zhang D ， Gan Y ， Li X and Zhu Y Y . 2021 . Source data-free domain adaptation of object detector through domain-specific perturbation . International Journal of Intelligent Systems ， 36 ： 3746 - 3766 ［ DOI： 10.1002/int.22434 http://dx.doi.org/10.1002/int.22434 ］
Xu W ， Huang H and Pan S . 2021 . Using feature alignment can improve clean average precision and adversarial robustness in object detection // In2021 IEEE International Conference on Image Processing （ICIP） . Alaska， USA ： IEEE： 2184 - 2188 ［ DOI： 10.1109/ICIP42928.2021.9506689 http://dx.doi.org/10.1109/ICIP42928.2021.9506689 ］
Xu W . 2017 . Feature squeezing： Detecting adversarial examples in deep neural networks ［EB/OL］. ［ 2017-04-04 ］. https://arxiv.org/abs/1704.01155 https://arxiv.org/abs/1704.01155
Yan C ， Chang X ， Luo M ， Liu H ， Zhang X and Zheng Q . 2022 . Semantics-guided contrastive network for zero-shot object detection . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 46 （ 3 ）： 1530 - 1544 ［ DOI： 10.1109/TPAMI.2021.3140070 http://dx.doi.org/10.1109/TPAMI.2021.3140070 ］
Yan C ， Zheng Q ， Chang X ， Luo M ， Yeh C H and Hauptman A G . 2020 . Semantics-preserving graph propagation for zero-shot object detection . IEEE Transactions on Image Processing ， 29 ： 8163 - 8176 ［ DOI： 10.1109/TIP.2020.3011807 http://dx.doi.org/10.1109/TIP.2020.3011807 ］
Yang D B ， Zhou Y ， Hong X P ， Zhang A T ， and Wang W P . 2023 . One-shot replay： Boosting incremental object detection via retrospecting one object // In Proceedings of the AAAI Conference on Artificial Intelligence . Singapore ： IEEE： 3127 – 3135 ［ DOI： 10.1609/aaai.v37i3.25417 http://dx.doi.org/10.1609/aaai.v37i3.25417 ］
Yang R ， and Yu Y . 2021 . Artificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis . Frontiers in oncology ， 11 ： 638182 ［ DOI： 10.1109/TMI.2021.3122835 http://dx.doi.org/10.1109/TMI.2021.3122835 ］
Yao L ， Han J ， Liang X ， Xu D ， Zhang W ， Li Z and Xu H . 2023 . Detclipv 2 ： Scalable open-vocabulary object detection pre-training via word-region alignment //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver， BC， Canada ： 23497 - 23506 ［ DOI： 10.48550/arXiv.2304.04514 http://dx.doi.org/10.48550/arXiv.2304.04514 ］
Yao L ， Han J ， Wen Y ， Liang X ， Xu D ， Zhang W ， Li Z ， Xu C ， Xu H . 2022 . Detclip： Dictionary-enriched visual-concept paralleled pre-training for open-world detection. Advances in Neural Information Processing Systems . New Orleans， LA， USA ： 35 ： 9125 - 9138 ［ DOI： 10.48550/arXiv.2209.09407 http://dx.doi.org/10.48550/arXiv.2209.09407 ］
Yao X X ， Zhao S C ， Xu P F and Yang J F . 2021 . Multi-source domain adaptation for object detection // Proceedings of 2021 IEEE/CVF International Conference on Computer Vision . Montreal， Canada ： IEEE： 3253 - 3262 ［ DOI： 10.1109/ICCV48922.2021.00326 http://dx.doi.org/10.1109/ICCV48922.2021.00326 ］
Yuan L ， Li X M ， Pan Z X ， Sun J M and Xiao L . 2022 . Review of adversarial examples for object detection ， 27 （ 10 ）： 2873 - 2896
袁珑 ， 李秀梅 ， 潘振雄 ， 孙军梅 ， 肖蕾 . 2022 . 面向目标检测的对抗样本综述 . 中国图象图形学报 ， 27 （ 10 ）： 2873 - 2896 ［ DOI： 10.11834/jig.210209 http://dx.doi.org/10.11834/jig.210209 ］
Yuan Z ， Wang L ， Ding W ， Zhang X ， Zhong J ， Ai J ， Li J and Zhu J . 2023 . Dualteacher： Bridging coexistence of unlabelled classes for semi-supervised incremental object detection ［EB/OL］. ［ 2023-12-13 ］. https://arxiv.org/abs/2401.05362 https://arxiv.org/abs/2401.05362
Zareian A ， Rosa KD ， Hu DH and Chang SF . 2021 . Open-vocabulary object detection using captions // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， TN， USA ： 14393 - 14402 ［ DOI： 10.48550/arXiv.2011.10678 http://dx.doi.org/10.48550/arXiv.2011.10678 ］
Zeng Z R ， Ding Y and Lu H T . 2024 . Enhancing cross-domain detection： adaptive class-aware contrastive transformer // Proceedings of the IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP） . Seoul， Korea ： IEEE： 6670 - 6674 ［ DOI： 10.1109/ICASSP48485.2024.10447182 http://dx.doi.org/10.1109/ICASSP48485.2024.10447182 ］
Zhang D ， Ye M ， Liu Y G ， Xiong L and Zhou L H . 2022 . Multi-source unsupervised domain adaptation for object detection . Information Fusion ， 78 ： 138 - 148 ［ DOI： 10.1016/j.inffus.2021.09.011 http://dx.doi.org/10.1016/j.inffus.2021.09.011 ］
Zhang H and Wang J . 2019 . Towards adversarially robust object detection // InProceedings of the IEEE/CVF International Conference on Computer Vision . Seoul， Korea ： IEEE： 421 - 430 ［ DOI： 10.48550/arXiv.1907.10310 http://dx.doi.org/10.48550/arXiv.1907.10310 ］
Zhang H ， Zhao Q ， Zheng L ， Zeng H ， Ge Z ， Li T and Xu S . 2024 . Exploring region-word alignment in built-in detector for open-vocabulary object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， WA， USA ： 16975 - 16984 ［ DOI： 10.1109/CVPR52733.2024.01606 http://dx.doi.org/10.1109/CVPR52733.2024.01606 ］
Zhang H . 2017 . mixup： Beyond empirical risk minimization ［EB/OL］.［ 2024-09-20 ］. https://www.arxiv.org/pdf/1710.09412.pdf https://www.arxiv.org/pdf/1710.09412.pdf
Zhang J ， Zhang J ， Ghosh S ， Li D ， Tasci S ， Heck L ， Zhang H ， Kuo C C . 2020 . Class-incremental learning via deep model consolidation // In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision . Colorado， USA ： IEEE： 1131 – 1140 ［ DOI： 10.48550/arXiv.1903.07864 http://dx.doi.org/10.48550/arXiv.1903.07864 ］
Zhang L B ， Zhou W Z ， Fan H ， Luo T J and Ling H B . 2024 . Robust domain adaptive object detection with unified multi-granularity alignment . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 1 ： 1 - 18 ［ DOI： 10.1109/TPAMI.2024.3416098 http://dx.doi.org/10.1109/TPAMI.2024.3416098 ］
Zhang S Q ， Zhang L and Liu Z Y . 2023 . Refined pseudo labeling for source-free domain adaptive object detection // Proceedings of the IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP） . Rhodes Island， Greece ： IEEE： 1 - 5 ［ DOI： 10.1109/ICASSP49357.2023.10096635 http://dx.doi.org/10.1109/ICASSP49357.2023.10096635 ］
Zhao S C ， Yao H Z ， Lin C ， Gao Y ， and Ding G G . 2024 . Multi-source-free Domain Adaptive Object Detection . International Journal of Computer Vision ， 1 ： 1 - 33 ［ DOI： 10.1007/s11263-024-02170-z http://dx.doi.org/10.1007/s11263-024-02170-z ］
Zhao X ， Liu X ， Wang D ， Gao Y and Liu Z . 2024 . Scene-adaptive and region-aware multi-modal prompt for open vocabulary object detection // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， WA， USA ： 16741 - 16750 ［ DOI： 10.1109/CVPR52733.2024.01584 http://dx.doi.org/10.1109/CVPR52733.2024.01584 ］
Zheng J ， Li W ， Hong J ， Petersson L and Barnes N . 2022 . Towards open-set object detection and discovery // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 3961 - 3970 ［ DOI： 10.48550/arXiv.2204.05604 http://dx.doi.org/10.48550/arXiv.2204.05604 ］
Zhong Y ， Yang J ， Zhang P ， Li C ， Codella N ， Li LH ， Zhou L ， Dai X ， Yuan L ， Li Y and Gao J . 2022 . Regionclip： Region-based language-image pretraining // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， LA， USA ： 16793 - 16803 ［ DOI： 10.48550/arXiv.2112.09106 http://dx.doi.org/10.48550/arXiv.2112.09106 ］
Zhu J Y ， Park T ， Isola P and Efros A A . 2017 . Unpaired image-to-image translation using cycle-consistent adversarial networks // Proceedings of 2017 IEEE International Conference on Computer Vision （ICCV） . Venice， Italy ： IEEE： 2223 - 2232 ［ DOI： 10.1109/ICCV.2017.244 http://dx.doi.org/10.1109/ICCV.2017.244 ］
Zhu P ， Wang H and Saligrama V . 2019 . Zero shot detection . IEEE Transactions on Circuits and Systems for Video Technology ， 30 （ 4 ）： 998 - 1010 ［ DOI： 10.1109/TCSVT.2019.2899569 http://dx.doi.org/10.1109/TCSVT.2019.2899569 ］
Zohar O ， Wang KC and Yeung S . 2023 . Prob： Probabilistic objectness for open world object detection // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Vancouver， Canada ： IEEE： 11444 – 11453 ［ DOI： 10.48550/arXiv.2212.01424 http://dx.doi.org/10.48550/arXiv.2212.01424 ］
Zou Z ， Chen K ， Shi Z ， Guo Y and Ye J . 2023 . Object detection in 20 years： A survey . Proceedings of the IEEE ， 111 （ 3 ）： 257 - 276 .［ DOI： 10.1109/JPROC.2023.3238524 http://dx.doi.org/10.1109/JPROC.2023.3238524 ］
相关作者
相关机构
京公网安备11010802024621