Abstract
Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from domain shift, especially when no labeled data is available in the target domain. To solve this problem, we propose an end-to-end cross-domain detection Transformer based on the mean teacher framework, MTTrans, which can fully exploit unlabeled target domain data in object detection training and transfer knowledge between domains via pseudo labels. We further propose the comprehensive multi-level feature alignment to improve the pseudo labels generated by the mean teacher framework taking advantage of the cross-scale self-attention mechanism in Deformable DETR. Image and object features are aligned at the local, global, and instance levels with domain query-based feature alignment (DQFA), bi-level graph-based prototype alignment (BGPA), and token-wise image feature alignment (TIFA). On the other hand, the unlabeled target domain data pseudo-labeled and available for the object detection training by the mean teacher framework can lead to better feature extraction and alignment. Thus, the mean teacher framework and the comprehensive multi-level feature alignment can be optimized iteratively and mutually based on the architecture of Transformers. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in three domain adaptation scenarios, especially the result of Sim10k to Cityscapes scenario is remarkably improved from 52.6 mAP to 57.9 mAP. Code will be released https://github.com/Lafite-Yu/MTTrans-OpenSource.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bai, Y., Mei, J., Yuille, A.L., Xie, C.: Are transformers more robust than cnns? Adv. Neural Inf. Process. Syst. 34, 26831–26843 (2021)
Cai, Q., et al.: Exploring object relation in mean teacher for cross-domain detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11457–11466 (2019)
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13
Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster r-cnn for object detection in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3339–3348 (2018)
Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. Ieee (2009)
Deng, J., Li, W., Chen, Y., Duan, L.: Unbiased mean teacher for cross-domain object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4091–4101 (2021)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)
Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., Zhang, Z.: Star-transformer. arXiv preprint arXiv:1902.09113 (2019)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hsu, C.-C., Tsai, Y.-H., Lin, Y.-Y., Yang, M.-H.: Every pixel matters: center-aware feature alignment for domain adaptive object detector. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 733–748. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_42
Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K., Vasudevan, R.: Driving in the matrix: can virtual worlds replace human-generated annotations for real world tasks? arXiv preprint arXiv:1610.01983 (2016)
Kim, T., Jeong, M., Kim, S., Choi, S., Kim, C.: Diversify and match: a domain adaptive representation learning paradigm for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12456–12465 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kirillov, A., He, K., Girshick, R., Rother, C., Dollár, P.: Panoptic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404–9413 (2019)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Luo, Z., et al.: Unsupervised domain adaptive 3D detection with multi-level consistency. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8866–8875 (2021)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Rezaeianaran, F., Shetty, R., Aljundi, R., Reino, D.O., Zhang, S., Schiele, B.: Seeking similarities over differences: similarity-based domain alignment for adaptive object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9204–9213 (2021)
Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6956–6965 (2019)
Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vision 126(9), 973–992 (2018)
Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural Inf. Process. Syst. 33, 596–608 (2020)
Sohn, K., Zhang, Z., Li, C.L., Zhang, H., Lee, C.Y., Pfister, T.: A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)
Sun, Q., et al.: Sugar: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In: Proceedings of the Web Conference 2021, pp. 2081–2091 (2021)
Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9627–9636 (2019)
Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)
Wang, W., et al.: Exploring sequence feature alignment for domain adaptive detection transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1730–1738 (2021)
Xu, C.D., Zhao, X.R., Jin, X., Wei, X.S.: Exploring categorical regularization for domain adaptive object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11724–11733 (2020)
Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3060–3069 (2021)
Xu, M., Wang, H., Ni, B., Tian, Q., Zhang, W.: Cross-domain detection via graph-induced prototype alignment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12355–12364 (2020)
Xu, T., Chen, W., Wang, P., Wang, F., Li, H., Jin, R.: Cdtrans: cross-domain transformer for unsupervised domain adaptation. arXiv preprint arXiv:2109.06165 (2021)
Yang, J., Liu, J., Xu, N., Huang, J.: Tvt: transferable vision transformer for unsupervised domain adaptation. arXiv preprint arXiv:2108.05988 (2021)
Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: point set representation for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9657–9666 (2019)
Yu, F., et al.: Bdd100k: a diverse driving video database with scalable annotation tooling, vol. 2, no. 5, p. 6. arXiv preprint arXiv:1805.04687 (2018)
Zhang, C., et al.: Delving deep into the generalization of vision transformers under distribution shifts. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7277–7286 (2022)
Zhang, J., Huang, J., Luo, Z., Zhang, G., Lu, S.: Da-detr: domain adaptive detection transformer by hybrid attention. arXiv preprint arXiv:2103.17084 (2021)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)
Zhong, C., Wang, J., Feng, C., Zhang, Y., Sun, J., Yokota, Y.: Pica: point-wise instance and centroid alignment based few-shot domain adaptive object detection with loose annotations. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2329–2338 (2022)
Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11106–11115 (2021)
Zhu, X., Pang, J., Yang, C., Shi, J., Lin, D.: Adapting object detectors via selective cross-domain alignment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 687–696 (2019)
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)
Acknowledgment
We thank Xiaoqi Li and Zhaoqing Wang for their help with the manuscript revision and the anonymous reviewers for their helpful comments to improve the paper. The authors of this paper are supported by the NSFC through grant No.U20B2053, and we also thanks the support from Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, J. et al. (2022). MTTrans: Cross-domain Object Detection with Mean Teacher Transformer. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13669. Springer, Cham. https://doi.org/10.1007/978-3-031-20077-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-20077-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20076-2
Online ISBN: 978-3-031-20077-9
eBook Packages: Computer ScienceComputer Science (R0)