|
|
基于深度学习的领域自适应目标检测算法研究
|
Abstract:
领域自适应目标检测是指在有标注的源领域训练一个目标检测模型，并将其迁移到无标注的目标领域的计算机视觉任务。它将领域自适应方法与目标检测技术相结合，解决了领域偏移导致的目标检测模型性能下降的问题，成为众多学者研究的焦点。本文对基于深度学习的域适应目标检测算法进行综述。首先介绍了域适应目标检测的研究背景，其次按照发展演变过程，阐述了近年来基于深度学习的经典域适应目标检测算法，并对其优劣进行分析对比，接着介绍了域适应目标检测的常用数据集。最后，我们通过详细的分析，对域适应目标检测具有潜力的几个发展方向进行探讨与展望。
Domain adaptive object detection refers to a computer vision task, which trains an object detection model on an annotated source domain and transfers the model to an unlabeled target domain. It combines domain adaptive methods with object detection techniques to solve the problem of performance degradation of object detection models caused by domain shift, and has become the focus of research by many researchers. This paper provides a review of domain adaptive object detection algorithms based on deep learning. Firstly, the research background of domain adaptive object detection is introduced. Secondly, according to the development and evolution process, we elaborate on some classic domain adaptive object detection algorithms based on deep learning in recent years. Furthermore, we analyze and compare the advantages and disadvantages of these algorithms. Then, the commonly used datasets of domain adaptive object detection are introduced. Finally, we discuss and prospect several potential development directions of domain adaptive object detection through detailed analysis.
| [1] | Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., et al. (2016) SSD: Single Shot Multibox Detector. In: Computer Vision—ECCV 2016, Amsterdam, 11-14 October 2016, 21-37. https://doi.org/10.1007/978-3-319-46448-0_2 |
| [2] | Ren, S., He, K., Girshick, R. and Sun, J. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1440-1448. |
| [3] | Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. https://doi.org/10.1109/cvpr.2016.91 |
| [4] | Tian, Z., Shen, C., Chen, H. and He, T. (2019) FCOS: Fully Convolutional One-Stage Object Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 9627-9636. https://doi.org/10.1109/iccv.2019.00972 |
| [5] | Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., et al. (2016) The Cityscapes Dataset for Semantic Urban Scene Understanding. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 3213-3223. https://doi.org/10.1109/cvpr.2016.350 |
| [6] | Sakaridis, C., Dai, D. and Van Gool, L. (2018) Semantic Foggy Scene Understanding with Synthetic Data. International Journal of Computer Vision, 126, 973-992. https://doi.org/10.1007/s11263-018-1072-8 |
| [7] | Long, M., Cao, Y., Wang, J. and Jordan, M. (2015) Learning Transferable Features with Deep Adaptation Networks. Proceedings of the International Conference on Machine Learning, Lille, France, 6-11 July 2015, 97-105. |
| [8] | Tzeng, E., Hoffman, J., Zhang, N., Saenko, K. and Darrell, T. (2014) Deep Domain Confusion: Maximizing for Domain Invariance. |
| [9] | Yan, H., Ding, Y., Li, P., Wang, Q., Xu, Y. and Zuo, W. (2017) Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 2272-2281. https://doi.org/10.1109/cvpr.2017.107 |
| [10] | Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F. and Vaughan, J.W. (2009) A Theory of Learning from Different Domains. Machine Learning, 79, 151-175. https://doi.org/10.1007/s10994-009-5152-4 |
| [11] | Shen, J., Qu, Y., Zhang, W. and Yu, Y. (2018) Wasserstein Distance Guided Representation Learning for Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, 2-7 February 2018, 4058-4065. |
| [12] | Ganin, Y. and Lempitsky, V. (2015) Unsupervised Domain Adaptation by Backpropagation. Proceedings of the International Conference on Machine Learning, Lille, France, 6-11 July 2015, 1180-1189. |
| [13] | Bousmalis, K., Silberman, N., Dohan, D., Erhan, D. and Krishnan, D. (2017) Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 22-25 July 2017, 3722-3731. https://doi.org/10.1109/cvpr.2017.18 |
| [14] | Chen, Y., Li, W., Sakaridis, C., Dai, D. and Van Gool, L. (2018) Domain Adaptive Faster R-CNN for Object Detection in the Wild. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 19-21 June 2018, 3339-3348. https://doi.org/10.1109/cvpr.2018.00352 |
| [15] | He, Z. and Zhang, L. (2019) Multi-Adversarial Faster-R CNN for Unrestricted Object Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 6668-6677. https://doi.org/10.1109/iccv.2019.00677 |
| [16] | Saito, K., Ushiku, Y., Harada, T. and Saenko, K. (2019) Strong-Weak Distribution Alignment for Adaptive Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 16-20 June 2019, 6956-6965. https://doi.org/10.1109/cvpr.2019.00712 |
| [17] | Xu, C., Zhao, X., Jin, X. and Wei, X. (2020) Exploring Categorical Regularization for Domain Adaptive Object Detection. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 14-19 June 2020, 11724-11733. https://doi.org/10.1109/cvpr42600.2020.01174 |
| [18] | Xu, M., Wang, H., Ni, B., Tian, Q. and Zhang, W. (2020) Cross-Domain Detection via Graph-Induced Prototype Alignment. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 14-19 June 2020, 12355-12364. https://doi.org/10.1109/cvpr42600.2020.01237 |
| [19] | Li, W., Liu, X. and Yuan, Y. (2022) SIGMA: Semantic-Complete Graph Matching for Domain Adaptive Object Detection. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 21-24 June 2022, 5291-5300. https://doi.org/10.1109/cvpr52688.2022.00522 |
| [20] | Rezaeianaran, F., Shetty, R., Aljundi, R., Reino, D.O., Zhang, S. and Schiele, B. (2021) Seeking Similarities over Differences: Similarity-Based Domain Alignment for Adaptive Object Detection. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 11-17 October 2021, 9204-9213. https://doi.org/10.1109/iccv48922.2021.00907 |
| [21] | Hsu, C., Tsai, Y., Lin, Y. and Yang, M. (2020) Every Pixel Matters: Center-Aware Feature Alignment for Domain Adaptive Object Detector. Computer Vision—ECCV 2020, Glasgow, 23-28 August 2020, 733-748. https://doi.org/10.1007/978-3-030-58545-7_42 |
| [22] | Tian, K., Zhang, C., Wang, Y., Xiang, S. and Pan, C. (2021) Knowledge Mining and Transferring for Domain Adaptive Object Detection. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 11-17 October 2021, 9133-9142. https://doi.org/10.1109/iccv48922.2021.00900 |
| [23] | Li, W., Liu, X. and Yuan, Y. (2023) SIGMA++: Improved Semantic-Complete Graph Matching for Domain Adaptive Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 9022-9040. https://doi.org/10.1109/tpami.2023.3235367 |
| [24] | Deng, J., Li, W., Chen, Y. and Duan, L. (2021) Unbiased Mean Teacher for Cross-Domain Object Detection. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 19-25 June 2021, 4091-4101. https://doi.org/10.1109/cvpr46437.2021.00408 |
| [25] | Li, Y., Dai, X., Ma, C., Liu, Y., Chen, K., Wu, B., et al. (2022) Cross-Domain Adaptive Teacher for Object Detection. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Montreal, 16-22 October 2022, 7581-7590. https://doi.org/10.1109/cvpr52688.2022.00743 |
| [26] | Zhao, L. and Wang, L. (2022) Task-specific Inconsistency Alignment for Domain Adaptive Object Detection. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 21-24 June 2022, 14217-14226. https://doi.org/10.1109/cvpr52688.2022.01382 |
| [27] | Jiang, J., Chen, B., Wang, J. and Long, M. (2021) Decoupled Adaptation for Cross-Domain Object Detection. |
| [28] | Liu, D., Zhang, C., Song, Y., Huang, H., Wang, C., Barnett, M., et al. (2023) Decompose to Adapt: Cross-Domain Object Detection via Feature Disentanglement. IEEE Transactions on Multimedia, 25, 1333-1344. https://doi.org/10.1109/tmm.2022.3141614 |
| [29] | Li, X., Chen, W., Xie, D., Yang, S., Yuan, P., Pu, S., et al. (2021) A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 8474-8481. https://doi.org/10.1609/aaai.v35i10.17029 |
| [30] | Huang, J., Guan, D., Xiao, A. and Lu, S. (2021) Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), 6-14 December 2021, 3635-3649. |
| [31] | Li, S., Ye, M., Zhu, X., Zhou, L. and Xiong, L. (2022) Source-Free Object Detection by Learning to Overlook Domain Style. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 21-24 June 2022, 8014-8023. https://doi.org/10.1109/cvpr52688.2022.00785 |
| [32] | VS, V., Oza, P. and Patel, V.M. (2023) Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 18-22 June 2023, 3520-3530. https://doi.org/10.1109/cvpr52729.2023.00343 |
| [33] | VS, V., Oza, P. and Patel, V.M. (2023) Towards Online Domain Adaptive Object Detection. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, 3-7 January 2023, 478-488. https://doi.org/10.1109/wacv56688.2023.00055 |
| [34] | Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K. and Vasudevan, R. (2017) Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks? 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 29 May-3 June 2017, 746-753. https://doi.org/10.1109/icra.2017.7989092 |
| [35] | Geiger, A., Lenz, P. and Urtasun, R. (2012) Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, 16-21 June 2012, 3354-3361. https://doi.org/10.1109/cvpr.2012.6248074 |
| [36] | Yu, F., Xian, W., Chen, Y., Liu, F., Liao, M., Madhavan, V. and Darrell, T. (2018) Bdd100k: A Diverse Driving Video Database with Scalable Annotation Tooling. |
| [37] | Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J. and Zisserman, A. (2014) The Pascal Visual Object Classes Challenge: A Retrospective. International Journal of Computer Vision, 111, 98-136. https://doi.org/10.1007/s11263-014-0733-5 |
| [38] | Inoue, N., Furuta, R., Yamasaki, T. and Aizawa, K. (2018) Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-22 June 2018, 5001-5009. https://doi.org/10.1109/cvpr.2018.00525 |
