journal article·2024-03-28Open access

Diverse Feature-Level Guidance Adjustments for Unsupervised Domain Adaptative Object Detection

Yuhe Zhu, Chang Liu, Yunfei Bai, Caiju Wang, Chengwei Wei, Zhenglin Li, Yang Zhou

Applied Sciences· Volume 14· Issue 7

Abstract

Unsupervised Domain Adaptative Object Detection (UDAOD) aims to alleviate the gap between the source domain and the target domain. Previous methods sought to plainly align global and local features across domains but adapted numerous pooled features and overlooked contextual information, which caused incorrect perceptions of foreground information. To tackle these problems, we propose Diverse Feature-level Guidance Adjustments (DFGAs) for two-stage object detection frameworks, including Pixel-wise Multi-scale Alignment (PMA) and Adaptative Threshold Confidence Adjustment (ATCA). Specifically, PMA adapts features within diverse hierarchical levels to capture sufficient contextual information. Through a customized PMA loss, features from different stages of a network facilitate information interaction across domains. Training with this loss function contributes to the generation of more domain-agnostic features. To better recognize foreground and background samples, ATCA employs adaptative thresholds to divide the foreground and background samples. This strategy flexibly instructs the classifier to perceive the significance of box candidates. Comprehensive experiments are conducted on Cityscapes, Foggy Cityscapes, KITTI, and Sim10k datasets to further demonstrate the superior performance of our method compared to the baseline method.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Video Surveillance and Tracking Methods

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China

Institute of Artifcial Intelligence, Shanghai University, Shanghai 200444, China

School of Future Technology, Shanghai University, Shanghai 200444, China

Funding

Young Scientists Fund of the National Natural Science Foundation of China · Shanghai Sailing Program · National Natural Science Foundation of China

References (42)

Show source-provided references
1. Chen, Y., Li, W., Sakaridis, C., Dai, D., and Van Gool, L. (2018, January 18–23). Domain adaptive faster r-cnn for object detection in the wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00352 ↗
2. Domain-adversarial training of neural networks
3. Chen, C., Zheng, Z., Huang, Y., Ding, X., and Yu, Y. (2021, January 20–25). I3net: Implicit instance-invariant network for adapting one-stage object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01239 ↗
4. Zhang, S., Tuo, H., Hu, J., and Jing, Z. (2021, January 8–11). Domain adaptive YOLO for one-stage cross-domain detection. Proceedings of the Asian Conference on Machine Learning. PMLR, London, UK.
5. Hsu, C.C., Tsai, Y.H., Lin, Y.Y., and Yang, M.H. (2020, January 23–28). Every pixel matters: Center-aware feature alignment for domain adaptive object detector. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part IX 16.10.1007/978-3-030-58545-7_42 ↗
6. Hnewa, M., and Radha, H. (2021, January 19–22). Multiscale domain adaptive yolo for cross-domain object detection. Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AL, USA.10.1109/ICIP42928.2021.9506039 ↗
7. Liu, W., Ren, G., Yu, R., Guo, S., Zhu, J., and Zhang, L. (2022, January 20–27). Image-adaptive YOLO for object detection in adverse weather conditions. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.10.1609/aaai.v36i2.20072 ↗
8. Xu, C.D., Zhao, X.R., Jin, X., and Wei, X.S. (2020, January 13–19). Exploring categorical regularization for domain adaptive object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01174 ↗
9. Zhou, W., Du, D., Zhang, L., Luo, T., and Wu, Y. (2022, January 18–24). Multi-granularity alignment domain adaptation for object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00936 ↗
10. Sindagi, V.A., Oza, P., Yasarla, R., and Patel, V.M. (2020, January 23–28). Prior-based domain adaptive object detection for hazy and rainy conditions. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XIV 16.10.1007/978-3-030-58568-6_45 ↗
11. Jiang, J., Chen, B., Wang, J., and Long, M. (2021). Decoupled adaptation for cross-domain object detection. arXiv.
12. He, Z., and Zhang, L. (2020, January 23–28). Domain adaptive object detection via asymmetric tri-way faster-rcnn. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XXIV 16.10.1007/978-3-030-58586-0_19 ↗
13. Li, S., Huang, J., Hua, X.S., and Zhang, L. (2021, January 2–9). Category dictionary guided unsupervised domain adaptation for object detection. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.10.1609/aaai.v35i3.16290 ↗
14. Saito, K., Ushiku, Y., Harada, T., and Saenko, K. (2019, January 15–20). Strong-weak distribution alignment for adaptive object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00712 ↗
15. Vs, V., Gupta, V., Oza, P., Sindagi, V.A., and Patel, V.M. (2021, January 19–25). Mega-cda: Memory guided attention for category-aware unsupervised domain adaptive object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR46437.2021.00449 ↗
16. Zhao, L., and Wang, L. (2022, January 18–24). Task-specific inconsistency alignment for domain adaptive object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01382 ↗
17. Faster r-cnn: Towards real-time object detection with region proposal networks
18. Diverse receptive field network with context aggregation for fast object detection10.1016/j.jvcir.2020.102770 ↗
19. Object detection in 20 years: A survey10.1109/JPROC.2023.3238524 ↗
20. Bulbul, M.F., Tabussum, S., Ali, H., Zheng, W., Lee, M.Y., and Ullah, A. (2021). Exploring 3D human action recognition using STACOG on multi-view depth motion maps sequences. Sensors, 21.10.3390/s21113642 ↗
21. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
22. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part I 14.10.1007/978-3-319-46448-0_2 ↗
23. Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). Fcos: Fully convolutional one-stage object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
24. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
25. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
26. Cai, Z., and Vasconcelos, N. (2018, January 18–22). Cascade r-cnn: Delving into high quality object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00644 ↗
27. Mitigate the classification ambiguity via localization-classification sequence in object detection10.1016/j.patcog.2023.109418 ↗
28. Self-adversarial disentangling for specific domain adaptation
29. Menke, M., Wenzel, T., and Schwung, A. (2022). AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection. arXiv.10.1109/ITSC55140.2022.9922138 ↗
30. Yang, Y., and Soatto, S. (2020, January 14–19). Fda: Fourier domain adaptation for semantic segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Washington, DC, USA.10.1109/CVPR42600.2020.00414 ↗
31. Liu, R., Han, Y., Wang, Y., and Tian, Q. (2021). Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection. arXiv.
32. Hsu, H.K., Yao, C.H., Tsai, Y.H., Hung, W.C., Tseng, H.Y., Singh, M., and Yang, M.H. (2020, January 1–5). Progressive domain adaptation for object detection. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Village, CO, USA.10.1109/WACV45572.2020.9093358 ↗
33. Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.244 ↗
34. Shen, Z., Maheshwari, H., Yao, W., and Savvides, M. (2019). Scl: Towards accurate domain adaptive object detection via gradient detach based stacked complementary losses. arXiv.
35. Li, C., Du, D., Zhang, L., Wen, L., Luo, T., Wu, Y., and Zhu, P. (2020, January 23–28). Spatial attention pyramid network for unsupervised domain adaptation. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XIII 16.10.1007/978-3-030-58601-0_29 ↗
36. Sharma, A., Kalluri, T., and Chandraker, M. (2021, January 19–25). Instance level affinity-based transfer for unsupervised domain adaptation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR46437.2021.00532 ↗
37. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
38. Semantic foggy scene understanding with synthetic data10.1007/s11263-018-1072-8 ↗
39. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016, January 27–30). The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.350 ↗
40. Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16–21). Are we ready for autonomous driving? the kitti vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6248074 ↗
41. Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K., and Vasudevan, R. (2016). Driving in the matrix: Can virtual worlds replace human-generated annotations for real world tasks?. arXiv.10.1109/ICRA.2017.7989092 ↗
42. He, Z., and Zhang, L. (November, January 27). Multi-adversarial faster-rcnn for unrestricted object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.