Papers
Topics
Authors
Recent
2000 character limit reached

Object Detectors in the Open Environment: Challenges, Solutions, and Outlook (2403.16271v4)

Published 24 Mar 2024 in cs.CV

Abstract: With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detectors often operate in open environments, where crucial factors (e.g., data distribution, objective) that influence model learning are often changing. The dynamic and intricate nature of the open environment poses novel and formidable challenges to object detectors. Unfortunately, current research on object detectors in open environments lacks a comprehensive analysis of their distinctive characteristics, challenges, and corresponding solutions, which hinders their secure deployment in critical real-world scenarios. This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments. We initially identified limitations of key structural components within the existing detection pipeline and propose the open environment object detector challenge framework that includes four quadrants (i.e., out-of-domain, out-of-category, robust learning, and incremental learning) based on the dimensions of the data / target changes. For each quadrant of challenges in the proposed framework, we present a detailed description and systematic analysis of the overarching goals and core difficulties, systematically review the corresponding solutions, and benchmark their performance over multiple widely adopted datasets. In addition, we engage in a discussion of open problems and potential avenues for future research. This paper aims to provide a fresh, comprehensive, and systematic understanding of the challenges and solutions associated with open-environment object detectors, thus catalyzing the development of more solid applications in real-world scenarios. A project related to this survey can be found at https://github.com/LiangSiyuan21/OEOD_Survey.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (366)
  1. Z. Zou et al. Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055, 2019.
  2. Z. Zhao et al. Object detection with deep learning: A review. TNNLS, 2019.
  3. C. Szegedy et al. Deep neural networks for object detection. In NeurIPS, 2013.
  4. Yurtsever et al. A survey of autonomous driving: Common practices and emerging technologies. IEEE access, 2020.
  5. Esteva et al. A guide to deep learning in healthcare. Nature medicine, 2019.
  6. Tang et al. Video based face recognition using multiple classifiers. In Automatic Face and Gesture Recognition, 2004.
  7. Liu et al. Spatio-temporal embedding for statistical face recognition from video. In ECCV, 2006.
  8. Zhi-Hua Zhou. Open-environment machine learning. National Science Review, 2022.
  9. P. Oza et al. Unsupervised domain adaptation of object detectors: A survey. TPAMI, 2023.
  10. S. Ren et al. Faster r-cnn: Towards real-time object detection with region proposal networks. In NeurIPS, 2015.
  11. W. Liu et al. Ssd: Single shot multibox detector. In ECCV, 2016.
  12. J. Redmon et al. You only look once: Unified, real-time object detection. In CVPR, 2016.
  13. T.-Y. Lin et al. Focal loss for dense object detection. In ICCV, 2017.
  14. K. He et al. Mask R-CNN. TPAMI, 2020.
  15. P. Sun et al. Sparse r-cnn: End-to-end object detection with learnable proposals. In CVPR, 2021.
  16. K. Duan et al. Centernet: Keypoint triplets for object detection. In ICCV, 2019.
  17. Z. Tian et al. Fcos: Fully convolutional one-stage object detection. In ICCV, 2019.
  18. C. Zhu et al. Feature selective anchor-free module for single-shot object detection. In CVPR, 2019.
  19. T. Kong et al. Foveabox: Beyound anchor-based object detection. TIP, 2020.
  20. N. Carion et al. End-to-end object detection with transformers. In ECCV, 2020.
  21. X. Zhu et al. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159, 2020.
  22. T. Liang et al. Cbnet: A composite backbone network architecture for object detection. TIP, 2022.
  23. K. He et al. Deep residual learning for image recognition. In CVPR, 2016.
  24. M. Sandler et al. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR, 2018.
  25. A. Radford et al. Learning transferable visual models from natural language supervision. In ICML, 2021.
  26. X. Wei et al. Transferable adversarial attacks for image and video object detection. arXiv preprint arXiv:1811.12641, 2018.
  27. T.-Y. Lin et al. Feature pyramid networks for object detection. In CVPR, 2017.
  28. Z. Cai et al. Cascade r-cnn: Delving into high quality object detection. In CVPR, 2018.
  29. M. Tan et al. Efficientdet: Scalable and efficient object detection. In CVPR, 2020.
  30. S. Liu et al. Path aggregation network for instance segmentation. In CVPR, 2018.
  31. V. VS et al. Mega-cda: Memory guided attention for category-aware unsupervised domain adaptive object detection. In CVPR, 2021.
  32. B. Cui et al. Rt-net: replay-and-transfer network for class incremental object detection. Applied Intelligence, 2023.
  33. A. Athalye et al. Synthesizing robust adversarial examples. In ICML, 2018.
  34. J. Lin et al. Composite backdoor attack for deep neural network by mixing existing benign features. In ACM CCS, 2020.
  35. T. Kim et al. Diversify match: A domain adaptive representation learning paradigm for object detection. In CVPR, 2019.
  36. R. Khirodkar et al. Domain randomization for scene-specific car detection pose estimation. In WACV, 2019.
  37. A. Prakash et al. Structured domain randomization: Bridging the reality gap by context-aware synthetic data. In ICRA, 2019.
  38. H. Wang et al. AFAN: augmented feature alignment network for cross-domain object detection. TIP, 2021.
  39. H. Hsu et al. Progressive domain adaptation for object detection. In WACV, 2020.
  40. C. Chen et al. Harmonizing transferability discriminability for adapting object detectors. In CVPR, 2020.
  41. J. Zhu et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV, 2017.
  42. Y. Gao et al. Asyfod: An asymmetric adaptation paradigm for few-shot domain adaptive object detection. In CVPR, 2023.
  43. S. Huang et al. Auggan: Cross domain adaptation with gan-based data augmentation. In ECCV, 2018.
  44. V. Vidit et al. CLIP the gap: A single domain generalization approach for object detection. In CVPR, 2023.
  45. A. Rodriguez et al. Domain adaptation for object detection via style consistency. In BMVC, 2019.
  46. W. Yun et al. Target-style-aware unsupervised domain adaptation for object detection. RAL, 2021.
  47. F. Yu et al. SC-UDA: style content gaps aware unsupervised domain adaptation for object detection. In WACV, 2022.
  48. Y. Chen et al. Domain adaptive faster R-CNN for object detection in the wild. In CVPR, 2018.
  49. K. Saito et al. Strong-weak distribution alignment for adaptive object detection. In CVPR, 2019.
  50. X. Zhu et al. Adapting object detectors via selective cross-domain alignment. In CVPR, 2019.
  51. C. Xu et al. Exploring categorical regularization for domain adaptive object detection. In CVPR, 2020.
  52. C. Li et al. Spatial attention pyramid network for unsupervised domain adaptation. In ECCV, 2020.
  53. Z. He et al. Multi-adversarial faster-rcnn for unrestricted object detection. In ICCV, 2019.
  54. D. Nguyen et al. Domain-adaptive object detection via uncertainty-aware distribution alignment. In ACM MM, 2020.
  55. M. Fu et al. Deeply aligned adaptation for cross-domain object detection. arXiv preprint 2004.02093, 2020.
  56. Z. He et al. Domain adaptive object detection via asymmetric tri-way faster-rcnn. In ECCV, 2020.
  57. Z. Zhao et al. Adaptive object detection with dual multi-label prediction. In ECCV, 2020.
  58. F. Rezaeianaran et al. Seeking similarities over differences: Similarity-based domain alignment for adaptive object detection. In ICCV, 2021.
  59. J. Jiang et al. Decoupled adaptation for cross-domain object detection. In ICLR, 2022.
  60. W. Wang et al. Exploring sequence feature alignment for domain adaptive detection transformers. In ACM MM, 2021.
  61. L. Hou et al. Informative consistent correspondence mining for cross-domain weakly supervised object detection. In CVPR, 2021.
  62. L. Zhao et al. Task-specific inconsistency alignment for domain adaptive object detection. In CVPR, 2022.
  63. M. Xu et al. Cross-domain detection via graph-induced prototype alignment. In CVPR, 2020.
  64. Y. Zheng et al. Cross-domain object detection through coarse-to-fine feature adaptation. In CVPR, 2020.
  65. Y. Zhang et al. RPN prototype alignment for domain adaptive object detector. In CVPR, 2021.
  66. P. Su et al. Adapting object detectors with conditional domain normalization. In ECCV, 2020.
  67. A. Wu et al. Vector-decomposed disentanglement for domain-invariant object detection. In ICCV, 2021.
  68. A. Wu et al. Instance-invariant domain adaptive object detection via progressive disentanglement. TPAMI, 2022.
  69. A. Wu et al. Single-domain generalized object detection in urban scene via cyclic-disentangled self-distillation. In CVPR, 2022.
  70. A. RoyChowdhury et al. Automatic adaptation of object detectors to new domains using self-training. In CVPR, 2019.
  71. M. Khodabandeh et al. A robust learning approach to domain adaptive object detection. In ICCV, 2019.
  72. S. Kim et al. Self-training adversarial background regularization for unsupervised domain adaptive one-stage object detection. In ICCV, 2019.
  73. X. Li et al. A free lunch for unsupervised domain adaptive object detection without source data. In AAAI, 2021.
  74. S. Li et al. Category dictionary guided unsupervised domain adaptation for object detection. In AAAI, 2021.
  75. M. Munir et al. SSAL: synergizing between self-training adversarial learning for domain adaptive object detection. In NeurIPS, 2021.
  76. Y. Lu et al. Multi-view domain adaptive object detection on camera networks. In AAAI, 2023.
  77. Q. Cai et al. Exploring object relation in mean teacher for cross-domain detection. In CVPR, 2019.
  78. Y. Liu et al. Unbiased teacher for semi-supervised object detection. In ICLR, 2021.
  79. J. Deng et al. Unbiased mean teacher for cross-domain object detection. In CVPR, 2021.
  80. M. He et al. Cross domain object detection by target-perceived dual branch distillation. In CVPR, 2022.
  81. Y. Li et al. Cross-domain adaptive teacher for object detection. In CVPR, 2022.
  82. J. Wu et al. Target-relevant knowledge preservation for multi-source domain adaptive object detection. In CVPR, 2022.
  83. X. Yao et al. Multi-source domain adaptation for object detection. In ICCV, 2021.
  84. M. Kennerley et al. 2pcnet: Two-phase consistency training for day-to-night unsupervised domain adaptive object detection. In CVPR, 2023.
  85. Y. Pan et al. Transferrable prototypical networks for unsupervised domain adaptation. In CVPR, 2019.
  86. K. Bousmalis et al. Domain separation networks. In NeurIPS, 2016.
  87. G. French et al. Self-ensembling for visual domain adaptation. In ICLR, 2018.
  88. Bao et al. Evidential deep learning for open set action recognition. In ICCV, 2021.
  89. Bao et al. OpenTAL: Towards open set temporal action localization. In CVPR, 2022.
  90. Bao et al. Latent space energy-based model for fine-grained open set recognition. arXiv preprint arXiv:2309.10711, 2023.
  91. D. Miller et al. Dropout sampling for robust object detection in open-set conditions. In ICRA, 2018.
  92. D. Miller et al. Evaluating merging strategies for sampling-based uncertainty techniques in object detection. In ICRA, 2019.
  93. X. Du et al. Vos: Learning what you don’t know by virtual outlier synthesis. In ICLR, 2022.
  94. J. Han et al. Expanding low-density latent regions for open-set object detection. In CVPR, 2022.
  95. K. Joseph et al. Towards open world object detection. In CVPR, 2021.
  96. X. Du et al. Unknown-aware object detection: Learning what you don’t know from videos in the wild. In CVPR, 2022.
  97. Y. Liu et al. Open-set semi-supervised object detection. In ECCV, 2022.
  98. H. Shi et al. Proposalclip: unsupervised open-category object proposal generation via exploiting clip cues. In CVPR, 2022.
  99. A. Gupta et al. Ow-detr: Open-world detection transformer. In CVPR, 2022.
  100. Z. Wu et al. Uc-owod: Unknown-classified open world object detection. In ECCV, 2022.
  101. B. Su et al. Hsic-based moving weight averaging for few-shot open-set object detection. In ACMMM, 2023.
  102. P. Zhu et al. Zero shot detection. TCSVT, 2019.
  103. Q. Mao et al. Zero-shot object detection with attributes-based category similarity. TCSVT, 2020.
  104. A. Bansal et al. Zero-shot object detection. In ECCV, 2018.
  105. S. Rahman et al. Polarity loss: Improving visual-semantic alignment for zero-shot detection. 2022.
  106. Z. Li et al. Zero-shot object detection with textual descriptions. In AAAI, 2019.
  107. C. Yan et al. Semantics-preserving graph propagation for zero-shot object detection. IEEE Trans. Image Process., 2020.
  108. H. Nie et al. From node to graph: Joint reasoning on visual-semantic relational graph for zero-shot detection. In WACV, 2022.
  109. C. Yan et al. Semantics-guided contrastive network for zero-shot object detection. TPAMI, 2022.
  110. P. Huang et al. Robust region feature synthesizer for zero-shot object detection. In CVPR, 2022.
  111. H. Li et al. Zero-shot camouflaged object detection. TIP, 2023.
  112. A. Gupta et al. Generative multi-label zero-shot learning. TPAMI, 2023.
  113. A. Zareian et al. Open-vocabulary object detection using captions. In CVPR, 2021.
  114. X. Gu et al. Open-vocabulary object detection via vision and language knowledge distillation. In ICLR, 2022.
  115. Z. Ma et al. Open-vocabulary one-stage detection with hierarchical visual-language knowledge distillation. In CVPR, 2022.
  116. Y. Du et al. Learning to prompt for open-vocabulary object detection with vision-language model. In CVPR, 2022.
  117. W. Kuo et al. F-vlm: Open-vocabulary object detection upon frozen vision and language models. In ICLR, 2023.
  118. X. Wu et al. CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching. In CVPR, 2023.
  119. M. Gao et al. Open Vocabulary Object Detection with Pseudo Bounding-Box Labels. In ECCV, 2022.
  120. C. Feng et al. PromptDet: Towards Open-vocabulary Detection using Uncurated Images. In ECCV, 2022.
  121. LH. Li et al. Grounded language-image pre-training. In CVPR, 2022.
  122. Y. Zhong et al. Regionclip: Region-based language-image pretraining. In CVPR, 2022.
  123. Z. Wang et al. Detecting everything in the open world: Towards universal object detection. In CVPR, 2023.
  124. D. Kim et al. Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers. In CVPR, 2023.
  125. L. Yao et al. DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. In NeurIPS, 2022.
  126. L. Yao et al. DetCLIPv2: Scalable open-vocabulary object detection pre-training via word-region alignment. In CVPR, 2023.
  127. R. Jonschkowski et al. Patterns for learning with side information. arXiv preprint arXiv:1511.06429, 2015.
  128. D. Jayaraman et al. Zero-shot recognition with unreliable attributes. In NeurIPS, 2014.
  129. J. Pennington et al. Glove: Global vectors for word representation. In EMNLP, 2014.
  130. MA. Bravo et al. Open-vocabulary Attribute Detection. In CVPR, 2023.
  131. K. Chen et al. Towards Open-vocabulary Object Attribute Recognition. In CVPR, 2023.
  132. X. Zhou et al. Multi-target invisibly trojaned networks for visual recognition and detection. In IJCAI, 2021.
  133. Liang et al. Efficient adversarial attacks for visual object tracking. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVI 16, 2020.
  134. Wang et al. Diversifying the high-level features for better adversarial transferability. arXiv preprint arXiv:2304.10136, 2023.
  135. He et al. Generating transferable 3d adversarial point cloud via random perturbation factorization. In Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
  136. Lou et al. Hide in thicket: Generating imperceptible and rational adversarial perturbations on 3d point clouds. arXiv preprint arXiv:2403.05247, 2024.
  137. Muxue et al. Adversarial instance attacks for interactions between human and object. 2023.
  138. He et al. Sa-attack: Improving adversarial transferability of vision-language pre-training models via self-augmentation. arXiv preprint arXiv:2312.04913, 2023.
  139. Liu et al. Improving adversarial transferability by stable diffusion. arXiv preprint arXiv:2311.11017, 2023.
  140. Dong et al. Face encryption via frequency-restricted identity-agnostic attacks. In Proceedings of the 31st ACM International Conference on Multimedia, 2023.
  141. Adv-watermark: A novel watermark perturbation for adversarial examples. In ACMMM, 2020.
  142. C. Xie et al. Adversarial examples for semantic segmentation and object detection. In ICCV, 2017.
  143. Q. Liao et al. Category-wise attack: Transferable adversarial examples for anchor free object detection. arXiv preprint arXiv:2003.04367, 2020.
  144. J. Im Choi et al. Adversarial attack and defense of yolo detectors in autonomous driving scenarios. In IV, 2022.
  145. D. Wang et al. Daedalus: Breaking nonmaximum suppression in object detection via adversarial examples. IEEE TC, 2021.
  146. A. Shapira et al. Phantom sponges: Exploiting non-maximum suppression to attack deep object detectors. In ICCV, 2023.
  147. M. Yin et al. Adc: Adversarial attacks against object detection that evade context consistency checks. In WACV, 2022.
  148. Z. Cai et al. Context-aware transfer attacks for object detection. In AAAI, 2022.
  149. Z. Cai et al. Zero-query transfer attacks on context-aware object detectors. In CVPR, 2022.
  150. OM. Nezami et al. Pick-object-attack: Type-specific adversarial attack for object detection. CVIU, 2021.
  151. H. Xia et al. Ssmi: How to make objects of interest disappear without accessing object detectors? arXiv preprint arXiv:2206.10809, 2022.
  152. Liang et al. Generate more imperceptible adversarial examples for object detection. In ICML 2021 Workshop on Adversarial Machine Learning, 2021.
  153. S. Liang et al. A large-scale multiple-objective method for black-box attack against object detection. In ECCV, 2022.
  154. S. Liang et al. Parallel rectangle flip attack: A query-based black-box attack against object detection. arXiv preprint arXiv:2201.08970, 2022.
  155. H. Huang et al. T-sea: Transfer-based self-ensemble attack on object detection. In CVPR, 2023.
  156. A. Liu et al. Perceptual-sensitive gan for generating adversarial patches. In AAAI, 2019.
  157. X. Liu et al. Dpatch: An adversarial patch attack on object detectors. arXiv preprint arXiv:1806.02299, 2018.
  158. Y. Zhang et al. Adversarial semantic contour for object detection. arXiv preprint arXiv:2109.15009, 2021.
  159. Y. Zhao et al. Object hider: Adversarial patch attack against object detectors. arXiv preprint arXiv:2010.14974, 2020.
  160. Z. Zhu et al. You cannot easily catch me: A low-detectable adversarial patch for object detectors. arXiv preprint arXiv:2109.15177, 2021.
  161. J. Bao. Sparse adversarial attack to object detection. arXiv preprint arXiv:2012.13692, 2020.
  162. S. Wu et al. Dpattack: Diffused patch attacks against universal object detection. arXiv preprint arXiv:2010.11679, 2020.
  163. A. Liu et al. Bias-based universal adversarial patch attack for automatic check-out. In ECCV, 2020.
  164. S. Pavlitskaya et al. Feasibility of inconspicuous gan-generated adversarial patches against object detection. arXiv preprint arXiv:2207.07347, 2022.
  165. X-adv: Physical adversarial object attacks against x-ray prohibited item detection. In USENIX Security Symposium, 2023.
  166. I. Evtimov et al. Robust physical-world attacks on machine learning models. arXiv preprint arXiv:1707.08945, 2017.
  167. L. Huang et al. Universal physical camouflage attacks on object detectors. In CVPR, 2020.
  168. Z. Wu et al. Making an invisibility cloak: Real world adversarial attacks on object detectors. In ECCV, 2020.
  169. K. Xu et al. Adversarial t-shirt! evading person detectors in a physical world. In ECCV, 2020.
  170. Y. Zhao et al. Seeing isn’t believing: Towards more robust adversarial attack against real world object detectors. In ACM CCS, 2019.
  171. A. Maesumi et al. Learning transferable 3d adversarial cloaks for deep trained detectors. arXiv preprint arXiv:2104.11101, 2021.
  172. S. Chen et al. Shapeshifter: Robust physical adversarial attack on faster r-cnn object detector. In ECML PKDD, 2019.
  173. T. Wu et al. Physical adversarial attack on vehicle detector in the carla simulator. arXiv preprint arXiv:2007.16118, 2020.
  174. Y. Duan et al. Learning coated adversarial camouflages for object detectors. arXiv preprint arXiv:2109.00124, 2021.
  175. J. Wang et al. Dual attention suppression attack: Generate adversarial camouflage in physical world. In CVPR, 2021.
  176. Spatiotemporal attacks for embodied agents. In ECCV, 2020.
  177. Chen et al. Universal watermark vaccine: Universal adversarial perturbations for watermark protection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.
  178. Liang et al. Vl-trojan: Multimodal instruction backdoor attacks against autoregressive visual language models. arXiv preprint arXiv:2402.13851, 2024.
  179. Liang et al. Poisoned forgery face: Towards backdoor attacks on face forgery detection. arXiv preprint arXiv:2402.11473, 2024.
  180. Liu et al. Does few-shot learning suffer from backdoor attacks? arXiv preprint arXiv:2401.01377, 2023.
  181. Liu et al. Pre-trained trojan attacks for visual recognition. arXiv preprint arXiv:2312.15172, 2023.
  182. Liang et al. Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning. arXiv preprint arXiv:2311.12075, 2023.
  183. H. Ma et al. Dangerous cloaking: Natural trigger based backdoor attacks on object detectors in the physical world. arXiv preprint arXiv:2201.08619, 2022.
  184. S. Chan et al. Baddet: Backdoor attacks on object detection. In ECCV, 2022.
  185. C. Luo et al. Untargeted backdoor attack against object detection. arXiv preprint arXiv:2211.05638, 2022.
  186. Wang et al. Adaptive perturbation generation for multiple backdoors detection. arXiv preprint arXiv:2209.05244, 2022.
  187. H. Zhang et al. Towards adversarially robust object detection. In ICCV, 2019.
  188. W. Xu et al. Using feature alignment can improve clean average precision and adversarial robustness in object detection. In ICIP, 2021.
  189. X. Li et al. On the importance of backbone to the adversarial robustness of object detectors. arXiv preprint arXiv:2305.17438, 2023.
  190. X. Chen et al. Robust and accurate object detection via adversarial learning. In CVPR, 2021.
  191. W. Xu et al. Robust and accurate object detection via self-knowledge distillation. In ICIP, 2022.
  192. Z. Dong et al. Adversarially-aware robust object detector. ECCV, 2022.
  193. J. Cheng et al. Adversarial intensity awareness for robust object detection.
  194. P. Chen et al. Class-aware robust adversarial training for object detection. In CVPR, 2021.
  195. G. K. Dziugaite et al. A study of the effect of jpg compression on adversarial images. arXiv preprint arXiv:1608.00853, 2016.
  196. P.-H. Chiang et al. Adversarial pixel masking: A defense against physical attacks for pre-trained object detectors. In ACM MM, 2021.
  197. M. Naseer et al. Local gradients smoothing: Defense against localized adversarial attacks. In WACV, 2019.
  198. W. Xu et al. Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv preprint arXiv:1704.01155, 2017.
  199. P. Chiang et al. Detection as regression: Certified object detection with median smoothing. In NeurIPS, 2020.
  200. C. Xiang et al. Detectorguard: Provably securing object detectors against localized patch hiding attacks. In CCS, 2021.
  201. H. Han et al. Real-time robust video object detection system against physical-world adversarial attacks. arXiv preprint arXiv:2208.09195, 2022.
  202. J. Liu et al. Segment and complete: Defending object detectors against adversarial patch attacks with robust patch detection. In CVPR, 2022.
  203. G. Rossolini et al. Defending from physically-realizable adversarial attacks through internal over-activation analysis. In AAAI, 2023.
  204. Liu et al. Exploring the relationship between architectural design and adversarially robust generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.
  205. Sun et al. Improving robust fairness via balance adversarial training. In Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
  206. Fast propagation is better: Accelerating single-step adversarial training via sampling subnetworks. TIFs, 2024.
  207. Improving fast adversarial training with prior-guided knowledge. arXiv preprint arXiv:2304.00202, 2023.
  208. Las-at: adversarial training with learnable attack strategy. In CVPR, 2022.
  209. Revisiting and exploring efficient fast adversarial training via law: Lipschitz regularization and auto weight averaging. arXiv preprint arXiv:2308.11443, 2023.
  210. Training robust deep neural networks via adversarial noise propagation. TIP, 2021.
  211. Interpreting and improving adversarial robustness of deep neural networks with neuron sensitivity. IEEE Transactions on Image Processing, 2021.
  212. Towards defending multiple lp-norm bounded adversarial perturbations via gated batch normalization. International Journal of Computer Vision, 2023.
  213. C. Xie et al. Adversarial examples improve image recognition. In CVPR, 2020.
  214. B. Wu et al. Do wider neural networks really help adversarial robustness? In NeurIPS, 2021.
  215. B. Wu et al. Towards efficient adversarial training on vision transformers. arXiv preprint arXiv:2207.10498, 2022.
  216. E. Wong et al. Fast is better than free: Revisiting adversarial training. arXiv preprint arXiv:2001.03994, 2020.
  217. J. Shieh et al. Continual learning strategy in one-stage object detection framework based on experience replay for autonomous driving vehicle. Sensors, 2020.
  218. L. Yuyang et al. Augmented box replay: Overcoming foreground shift for incremental object detection. arXiv preprint arXiv:2307.12427, 2023.
  219. D. Yang et al. One-shot replay: boosting incremental object detection via retrospecting one object. In AAAI, 2023.
  220. M. Acharya et al. Rodeo: Replay for online object detection. arXiv preprint arXiv:2008.06439, 2020.
  221. J. Shieh et al. Utilizing incremental branches on a one-stage object detection framework to avoid catastrophic forgetting. MVA, 2022.
  222. Y. Liu et al. Continual detection transformer for incremental object detection. In CVPR, 2023.
  223. Y. Hao et al. An end-to-end architecture for class-incremental object detection with knowledge distillation. In ICME, 2019.
  224. DA. Ganea et al. Incremental few-shot instance segmentation. In CVPR, 2021.
  225. W. Li et al. Incremental learning of single-stage detectors with mining memory neurons. In ICCC, 2018.
  226. C. Peng et al. Diode: dilatable incremental object detection. PR, 2023.
  227. H. Chen et al. Lstd: A low-shot transfer detector for object detection. In AAAI, 2018.
  228. B. Kang et al. Few-shot object detection via feature reweighting. In ICCV, 2019.
  229. M. Cheng et al. Meta-learning-based incremental few-shot object detection. TCSVT, 2021.
  230. L. Yin et al. Sylph: A hypernetwork framework for incremental few-shot object detection. In CVPR, 2022.
  231. J. Perez-Rua et al. Incremental few-shot object detection. In CVPR, 2020.
  232. A. Tambwekar et al. Few-shot batch incremental road object detection via detector fusion. In ICCV, 2021.
  233. Z. Yang et al. Context-transformer: Tackling object confusion for few-shot detection. In AAAI, 2020.
  234. N. Zhang et al. Incremental learning of object detection with output merging of compact expert detectors. In ICoIAS, 2021.
  235. B. Yang et al. Continual object detection via prototypical task correlation guided gating mechanism. In CVPR, 2022.
  236. S. Rahman et al. Any-shot object detection. In ACCV, 2020.
  237. N. Dong et al. Incremental-detr: Incremental few-shot object detection via self-supervised learning. In AAAI, 2023.
  238. B. Cui et al. Balanced ranking and sorting for class incremental object detection. In ICASSP, 2022.
  239. L. Liu et al. Incdet: In defense of elastic weight consolidation for incremental object detection. TNNLS, 2020.
  240. K. Nguyen et al. ifs-rcnn: An incremental few-shot instance segmenter. In CVPR, 2022.
  241. K. Shmelkov et al. Incremental learning of object detectors without catastrophic forgetting. In ICCV, 2017.
  242. N. Dong et al. Bridging non co-occurrence with unlabeled in-the-wild data for incremental object detection. NeurIPS, 2021.
  243. P. Li et al. Class-incremental few-shot object detection. arXiv preprint arXiv:2105.07637, 2021.
  244. C. Peng et al. Sid: Incremental learning for anchor-free object detection via selective and inter-related distillation. CVIU, 2021.
  245. D. Yang et al. Multi-view correlation distillation for incremental object detection. PR, 2022.
  246. C. Peng et al. Faster ilod: Incremental learning for object detectors based on faster rcnn. PR letters, 2020.
  247. W. Zhou et al. Lifelong object detection. arXiv preprint arXiv:2009.01129, 2020.
  248. L. Chen et al. A new knowledge distillation for incremental object detection. In IJCNN, 2019.
  249. T. Feng et al. Overcoming catastrophic forgetting in incremental object detection via elastic response distillation. In CVPR, 2022.
  250. E. Verwimp et al. Re-examining distillation for continual object detection. arXiv preprint arXiv:2204.01407, 2022.
  251. Y. Li et al. Towards generalized and incremental few-shot object detection. arXiv preprint arXiv:2109.11336, 2021.
  252. K. Joseph et al. Incremental object detection via meta-learning. TPAMI, 2021.
  253. Y. She et al. Fast hierarchical learning for few-shot object detection. In IROS, 2022.
  254. Three types of incremental learning. Nature Machine Intelligence, 2022.
  255. F. Zhu et al. Class-incremental learning via dual augmentation. NeurIPS, 2021.
  256. A. Agarwal et al. Semantics-driven generative replay for few-shot class incremental learning. In ACM MM, 2022.
  257. JL. McClelland et al. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review, 1995.
  258. FM. Castro et al. End-to-end incremental learning. In ECCV, 2018.
  259. TL. Hayes et al. Memory efficient experience replay for streaming learning. In ICRA, 2019.
  260. S. Rebuffi et al. icarl: Incremental classifier and representation learning. In CVPR, 2017.
  261. Y. Wu et al. Large scale incremental learning. In CVPR, 2019.
  262. S. Yun et al. Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV, 2019.
  263. H. Zhang et al. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
  264. A. Bochkovskiy et al. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
  265. M. Biehl et al. Distance measures for prototype based classification. In IWBIC, 2013.
  266. A. Creswell et al. Generative adversarial networks: An overview. IEEE signal processing magazine, 2018.
  267. L. Wang et al. A comprehensive survey of continual learning: Theory, method and application. arXiv preprint arXiv:2302.00487, 2023.
  268. Q. Fan et al. Few-shot object detection with attention-rpn and multi-relation detector. In CVPR, 2020.
  269. R. Aljundi et al. Expert gate: Lifelong learning with a network of experts. In CVPR, 2017.
  270. M. Collier et al. Routing networks with co-training for continual learning. arXiv preprint arXiv:2009.04381, 2020.
  271. RA. Jacobs et al. Adaptive mixtures of local experts. Neural computation, 1991.
  272. N. Srivastava et al. Dropout: a simple way to prevent neural networks from overfitting. JMLR, 2014.
  273. H. Shon et al. Dlcft: Deep linear continual fine-tuning for general incremental learning. In ECCV, 2022.
  274. JO. Zhang et al. Side-tuning: a baseline for network adaptation via additive side networks. In ECCV, 2020.
  275. O. Ostapenko et al. Foundational models for continual learning: An empirical study of latent replay. arXiv preprint arXiv:2205.00329, 2022.
  276. VV. Ramasesh et al. Effect of scale on catastrophic forgetting in neural networks. In ICLR, 2021.
  277. S. Purushwalkam et al. The challenges of continuous self-supervised learning. In ECCV, 2022.
  278. J. Gallardo et al. Self-supervised training enhances online continual learning. arXiv preprint arXiv:2103.14010, 2021.
  279. J. Kirkpatrick et al. Overcoming catastrophic forgetting in neural networks. NAS, 2017.
  280. J. Schwarz et al. Progress & compress: A scalable framework for continual learning. In ICML, 2018.
  281. R. Aljundi et al. Memory aware synapses: Learning what (not) to forget. In ECCV, 2018.
  282. Liang et al. Exploring inconsistent knowledge distillation for object detection with data augmentation. In Proceedings of the 31st ACM International Conference on Multimedia, 2023.
  283. Li et al. Learning to optimize permutation flow shop scheduling via graph-based imitation learning. arXiv preprint arXiv:2210.17178, 2022.
  284. SI. Mirzadeh et al. Understanding the role of training regimes in continual learning. NeurIPS, 2020.
  285. J. Vanschoren. Meta-learning. Automated machine learning: methods, systems, challenges, 2019.
  286. K. Javed et al. Meta-learning representations for continual learning. NeurIPS, 2019.
  287. M. Riemer et al. Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910, 2018.
  288. J. Rajasegaran et al. itaml: An incremental task-agnostic meta-learning approach. In CVPR, 2020.
  289. M. Everingham et al. The PASCAL Visual Object Classes (VOC) Challenge. IJCV, 2010.
  290. T. Lin et al. Microsoft COCO: Common Objects in Context. In ECCV, 2014.
  291. M. Johnson-Roberson et al. Driving in the matrix: Can virtual worlds replace human-generated annotations for real world tasks? arXiv preprint arXiv:1610.01983, 2016.
  292. M. Cordts et al. The cityscapes dataset for semantic urban scene understanding. In CVPR, 2016.
  293. C. Sakaridis et al. Semantic foggy scene understanding with synthetic data. International Journal of Computer Vision, 2018.
  294. A. Geiger et al. Vision meets robotics: The kitti dataset. Int J Rob Res, 2013.
  295. H. Xu et al. End-to-end learning of driving models from large-scale video datasets. In CVPR, 2017.
  296. N. Inoue. Cross-domain weakly-supervised object detection through progressive domain adaptation. In CVPR, 2018.
  297. D. Lam et al. xview: Objects in context in overhead imagery. arXiv preprint arXiv:1802.07856, 2018.
  298. W. Li et al. SIGMA: semantic-complete graph matching for domain adaptive object detection. In CVPR, 2022.
  299. G. Zhao et al. Collaborative training between region proposal localization classification for domain adaptive object detection. In ECCV, 2020.
  300. K. Tian et al. Knowledge mining transferring for domain adaptive object detection. In ICCV, 2021.
  301. S. Cao et al. Contrastive mean teacher for domain adaptive object detectors. In CVPR, 2023.
  302. Y. Liu et al. CIGAR: cross-modality graph reasoning for domain adaptive object detection. In CVPR, 2023.
  303. C. Chen et al. Relation matters: Foreground-aware graph-based relational reasoning for domain adaptive object detection. TPAMI, 2023.
  304. S. Zhao et al. Exploiting unlabeled data with vision and language models for object detection. In ECCV, 2022.
  305. Y. Zang et al. Open-vocabulary detr with conditional matching. In ECCV, 2022.
  306. Y. Zang et al. Simple open-vocabulary object detection. In ECCV, 2022.
  307. H. Bangalath et al. Bridging the gap between object and image-level representations for open-vocabulary detection. In NeurIPS, 2022.
  308. A. Gupta et al. LVIS: A dataset for large vocabulary instance segmentation. In CVPR, 2019.
  309. M. Everingham. The pascal visual object classes challenge,(voc2007) results. http://pascallin. ecs. soton. ac. uk/challenges/VOC/voc2007/index. html., 2007.
  310. Ma et al. Codet: Co-occurrence guided region-word alignment for open-vocabulary object detection. In NeurIPS, 2024.
  311. Menon et al. Visual classification via description from large language models. In ICLR, 2023.
  312. Chen et al. Sim2word: Explaining similarity with representative attribute words via counterfactual explanations. ACM Transactions on Multimedia Computing, Communications and Applications, 2023.
  313. Chen et al. Less is more: Fewer interpretable region via submodular subset selection. In ICLR, 2024.
  314. Drive: Deep reinforced accident anticipation with visual explanation. In ICCV, 2021.
  315. Li et al. DISC: Learning from noisy labels via dynamic instance-specific selection and correction. In CVPR, 2023.
  316. K. Fujii et al. Adversarially trained object detector for unsupervised domain adaptation. IEEE Access, 2022.
  317. Jiao et al. A survey of deep learning-based object detection. IEEE access, 2019.
  318. Liu et al. Deep learning for generic object detection: A survey. IJCV, 2020.
  319. Kaur et al. A comprehensive review of object detection with deep learning. Digital Signal Processing, 2023.
  320. Padilla et al. A comparative analysis of object detection metrics with a companion open-source toolkit. Electronics, 2021.
  321. Dhillon et al. Convolutional neural network: a review of models, methodologies and applications to object detection. Progress in Artificial Intelligence, 2020.
  322. Cheng et al. Towards large-scale small object detection: Survey and benchmarks. TPAMI, 2023.
  323. Oksuz et al. Imbalance problems in object detection: A review. TPAMI, 2020.
  324. Tong et al. Recent advances in small object detection based on deep learning: A review. Image and Vision Computing, 2020.
  325. Mittal et al. Deep learning-based object detection in low-altitude uav datasets: A survey. Image and Vision computing, 2020.
  326. Oza et al. Unsupervised domain adaptation of object detectors: A survey. TPAMI, 2023.
  327. Menezes et al. Continual object detection: a review of definitions, strategies, and challenges. Neural networks, 2023.
  328. Amirkhani et al. A survey on adversarial attacks and defenses for object detection and their applications in autonomous vehicles. The Visual Computer, 2023.
  329. Krizhevsky et al. Imagenet classification with deep convolutional neural networks. NeurIPS, 2012.
  330. Zeiler et al. Visualizing and understanding convolutional networks. In ECCV, 2014.
  331. Szegedy et al. Going deeper with convolutions. In CVPR, 2015.
  332. R. Gurbaxani et al. Traits & transferability of adversarial examples against instance segmentation & object detection. arXiv preprint arXiv:1808.01452, 2018.
  333. M. Lee et al. On physical adversarial patches for object detection. arXiv preprint arXiv:1906.11897, 2019.
  334. Y. Zhang et al. Camou: Learning a vehicle camouflage for physical adversarial attack on object detections in the wild. ICLR, 2019.
  335. A. Saha et al. Role of spatial context in adversarial robustness for object detection. In CVPRW, 2020.
  336. S. Hoory et al. Dynamic adversarial patch for evading object detection models. arXiv preprint arXiv:2010.13070, 2020.
  337. A. Zolfi et al. The translucent patch: A physical and universal attack on object detectors. In CVPR, 2021.
  338. S. Pavlitskaya et al. Suppress with a patch: Revisiting universal adversarial patch attacks against object detection. In ICECCME, 2022.
  339. GS. Hartnett et al. Empirical evaluation of physical adversarial patch attacks against overhead object detection models. arXiv preprint arXiv:2206.12725, 2022.
  340. P. Labarbarie et al. Benchmarking and deeper analysis of adversarial patch attack on object detectors. In IJCAIW, 2022.
  341. A. Du et al. Physical adversarial attacks on an aerial imagery object detector. In WACV, 2022.
  342. A. Shapira et al. Attacking object detector using a universal targeted label-switch patch. arXiv preprint arXiv:2211.08859, 2022.
  343. Y. Zhang et al. Transferable physical attack against object detection with separable attention. arXiv preprint arXiv:2205.09592, 2022.
  344. Z. Hu et al. Adversarial texture for fooling person detectors in the physical world. In CVPR, 2022.
  345. H. Ma et al. Macab: Model-agnostic clean-annotation backdoor to object detection with natural trigger in real-world. arXiv preprint arXiv:2209.02339, 2022.
  346. H. Wu et al. Adversarial detection: Attacking object detection in real time. arXiv preprint arXiv:2209.01962, 2022.
  347. J. Sun et al. Differential evolution based dual adversarial camouflage: Fooling human eyes and object detectors. NN, 2023.
  348. D. Li et al. Rilod: Near real-time incremental learning for object detection at the edge. In SEC, 2019.
  349. F. Cermelli et al. Modeling missing annotations for incremental learning in object detection. In CVPR, 2022.
  350. Radosavovic et al. Designing network design spaces. In CVPR, 2020.
  351. F. Yu et al. BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning. In CVPR, 2020.
  352. A. Kuznetsova et al. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. IJCV, 2020.
  353. Liu et al. Energy-based out-of-distribution detection. In NeurIPS, 2020.
  354. Tack et al. CSI: Novelty detection via contrastive learning on distributionally shifted instances. In NeurIPS, 2020.
  355. A. Dhamija et al. The overlooked elephant of object detection: Open set. In WACV, 2020.
  356. C. Chen et al. Dual bipartite graph learning: A general approach for domain adaptive object detection. In ICCV, 2021.
  357. F. Liu et al. Domain contrast for domain adaptive object detection. TCSVT, 2022.
  358. S. Rahman et al. Transductive learning for zero-shot object detection. In ICCV, 2019.
  359. Y. Zheng et al. Background learnable cascade for zero-shot object detection. In ACCV, 2020.
  360. S. Rahman et al. Zero-shot object detection: Joint recognition and localization of novel concepts. Int. J. Comput. Vis., 2020.
  361. S. Zhao et al. Gtnet: Generative transfer network for zero-shot object detection. In AAAI, 2020.
  362. P. Zhu et al. Don’t even look once: Synthesizing features for zero-shot detection. In CVPR, 2020.
  363. Y. Zheng et al. Visual language based succinct zero-shot object detection. In ACMMM, 2021.
  364. X. Wang et al. Frustratingly simple few-shot object detection. arXiv preprint arXiv:2003.06957, 2020.
  365. S. Antonelli et al. Few-shot object detection: A survey. (SUR, 2022.
  366. A. Wu et al. Universal-prototype enhancing for few-shot object detection. In ICCV, 2021.
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up