Cross-Domain Attention Alignment for Domain Adaptive Person re-ID
Authors: 
Zhen Zhang, Wei Wang, Guoliang KangAuthors Info & Claims
Pages 114 - 127
Abstract
Domain adaptive person re-identification (re-ID) aims to re-identify persons across domains with distinct distributions. The key to this task lies in how to effectively mitigate the domain gap between source and target domain. We observe that the attention of a network, which is crucial for identifying a person, may shift from source to target. Previous works don’t explicitly model and mitigate the shift of attention mechanism, largely constraining the re-ID performance. To address this issue, we propose to align the attention mechanism across domains to reduce the domain gap and facilitate the person re-ID. Specifically, we assume that the discriminative parts of a person should be consistent across domains with different styles. We firstly adopt CycleGAN to acquire paired images with different domain styles. Then we minimize the distance of attention maps across domains to rectify the attention shift. Extensive experiments demonstrate that our method performs favorably against previous state-of-the-arts.
References
[1]
Zhang, Z., Lan, C., Zeng, W., Jin, X., Chen, Z.: Relation-aware global attention for person re-identification. In: CVPR, pp. 3186–3195 (2020)
[2]
Luo H, Jiang W, Youzhi G, Liu F, Liao X, Lai S, and Jianyang G A strong baseline and batch normalization neck for deep person re-identification IEEE TMM 2019 22 10 2597-2609
[3]
Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: CVPR, pp. 994–1003 (2018)
[4]
Huang, Y., Wu, Q., Xu, J., Zhong, Y.: SBSGAN: suppression of inter-domain background shift for person re-identification. In: ICCV, pp. 9527–9536 (2019)
[5]
Lin, S., Li, H., Li, C.T., Kot, A.C.: Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. In: BMVC (2018)
[6]
Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR, pp. 2275–2284 (2018)
[7]
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: ICML, pp. 97–105. PMLR (2015)
[8]
Dai, Y., Liu, J., Sun, Y., Tong, Z., Zhang, C., Duan, L.Y.: IDM: an intermediate domain module for domain adaptive person re-id. In: ICCV, pp. 11864–11874 (2021)
[9]
Luo, C., Song, C., Zhang, Z.: Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. In: ECCV, pp. 224–241. Springer, Berlin (2020)
[10]
Zhang X, Ma J, Liu H, Hai-Miao H, and Yang P Dual attentional Siamese network for visual tracking Displays 2022 74
[11]
Zhang X, Dou X, Zhao X, Li G, and Wang Z Instance-aware diversity feature generation for unsupervised person re-identification Displays 2024 83
[12]
Kang, G., Zheng, L., Yan, Y., Yang, Y.: Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target expectation maximization. In: ECCV, pp. 401–416 (2018)
[13]
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. NeurIPS 29 (2016)
[14]
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML, pp. 2208–2217. PMLR (2017)
[15]
Sun, B., Saenko, K.: Deep coral: correlation alignment for deep domain adaptation. In: ECCV, pp. 443–450. Springer, Berlin (2016)
[16]
Chen, C., Zhihang, F., Chen, Z., Jin, S., Cheng, Z., Jin, X., Hua, X.-S.: Homm: higher-order moment matching for unsupervised domain adaptation. In: AAAI, vol. 34, pp. 3422–3429 (2020)
[17]
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML, pp. 2208–2217. PMLR (2017)
[18]
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189. PMLR (2015)
[19]
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 7167–7176 (2017)
[20]
Zheng, K., Lan, C., Zeng, W., Zhang, Z., Zha, Z.-J.: Exploiting sample uncertainty for domain adaptive person re-identification. In: AAAI, vol. 35, pp. 3538–3546 (2021)
[21]
Zheng, K., Liu, W., He, L., Mei, T., Luo, J., Zha, Z.J.: Group-aware label transfer for domain adaptive person re-identification. In: CVPR, pp. 5310–5319 (2021)
[22]
Han, J., Li, Y.-L., Wang, S.: Delving into probabilistic uncertainty for unsupervised domain adaptive person re-identification. In: AAAI, vol. 36, pp. 790–798 (2022)
[23]
He, T., Shen, L., Guo, Y., Ding, G., Guo, Z.: Secret: Self-consistent pseudo label refinement for unsupervised domain adaptive person re-identification. In: AAAI, vol. 36, pp. 879–887 (2022)
[24]
Zha, L., Chen, Y., Zhou, P., Zhang, Y.: Intensifying the consistency of pseudo label refinement for unsupervised domain adaptation person re-identification. In: ICME, pp. 1547–1552. IEEE (2023)
[25]
Li, Z., Shi, Y., Ling, H., Chen, J., Wang, Q., Zhou, F.: Reliability exploration with self-ensemble learning for domain adaptive person re-identification. In: AAAI, vol. 36, pp. 1527–1535 (2022)
[26]
Ge Y, Zhu F, Chen D, Zhao R, et al. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id NeurIPS 2020 33 11309-11321
[27]
Yuhang, W., Huang, T., Yao, H., Zhang, C., Shao, Y., Han, C., Gao, C., Sang, N.: Multi-centroid representation network for domain adaptive person re-id. In: AAAI, vol. 36, pp. 2750–2758 (2022)
[28]
Lee, G., Lee, S., Kim, D., Shin, Y., Yoon, Y., Ham, B.: Camera-driven representation learning for unsupervised domain adaptive person re-identification. In: ICCV, pp. 11453–11462 (2023)
[29]
Isobe, T., Li, D., Tian, L., Chen, W., Shan, Y., Wang, S.: Towards discriminative representation learning for unsupervised person re-identification. In: ICCV, pp. 8526–8536 (2021)
[30]
Zheng, Y., Tang, S., Teng, G., Ge, Y., Liu, K., Qin, J., Qi, D., Chen, D.: Online pseudo label generation by hierarchical cluster dynamics for adaptive person re-identification. In: ICCV, pp. 8371–8381 (2021)
[31]
Huang, Y., Peng, P., Jin, Y., Li, Y., Xing, J.: Domain adaptive attention learning for unsupervised person re-identification. In: AAAI, vol. 34, pp. 11069–11076 (2020)
[32]
Ester, M., Kriegel, H.-P., Sander, J., Xiaowei, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD, vol. 96, pp. 226–231 (1996)
[33]
Dai, Z., Wang, G., Yuan, W., Zhu, S., Tan, P.: Cluster contrast for unsupervised person re-identification. In: ACCV, pp. 1142–1160 (2022)
[34]
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV, pp. 1116–1124 (2015)
[35]
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV, pp. 3754–3762 (2017)
[36]
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR, pp. 79–88 (2018)
[37]
Wang, X., Doretto, G., Sebastian, T., Rittscher, J., Tu, P.: Shape and appearance context modeling. In: ICCV, pp. 1–8. IEEE (2007)
[38]
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248–255. IEEE (2009)
[39]
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
[40]
Radenović F, Tolias G, and Chum O Fine-tuning CNN image retrieval with no human annotation IEEE Trans. Pattern Anal. Mach. Intell. 2018 41 7 1655-1668
Index Terms
- Cross-Domain Attention Alignment for Domain Adaptive Person re-ID
Index terms have been assigned to the content through auto-classification.
Recommendations
Person Re-identification Method Based on Cross-domain Image Style Conversion
ICDSP '20: Proceedings of the 2020 4th International Conference on Digital Signal ProcessingThe existing cross-domain person re-identification technology has a large difference between the source domain and the target domain, and the performance of the model trained in single-domain is significantly reduced when directly used on another ...
Attention-calibration based double-branch cross-domain person re-identification
AbstractExisting cross-domain pedestrian re-identification methods tend to utilize domain adaptation or domain generalization strategies to eliminate the differences between domains, but these methods fail to fully characterize the ...
Cross-dataset person re-identification using deep convolutional neural networks: effects of context and domain adaptation
Over the past years, the impact of surveillance systems on public safety increases dramatically. One significant challenge in this domain is person re-identification, which aims to detect whether a person has already been captured by another camera in ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Oct 2024
595 pages
ISBN:978-981-97-8857-6
DOI:10.1007/978-981-97-8858-3
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 03 November 2024
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 22 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in