Representation strategy for unsupervised domain adaptation on person re-identification

Abstract

The task of unsupervised person re-identification (Re-ID) is to transfer the knowledge learned in the source domain with no labels to the target domain with no labels. Due to the significant differences in the background of different datasets, the trained model is challenging to extract person features accurately on unsupervised domain adaptive (UDA). Most UDA methods for person Re-ID use single-image representation (SIR) during the feature extraction. These methods might ignore the difference among the cross-view images with the same identity. For this problem, the joint learning image representation strategy for unsupervised domain adaptation (JLIRS-UDA) is proposed, which takes cross-image representation (CIR) into account for UDA. The network architecture of JLIRS-UDA consists of two networks with branching networks. Each network consists of a shared network and two branching networks, the SIR branch and CIR branch. The two branching networks aim to learn the SIR and CIR, respectively. To ensure the accuracy of the pseudo-label generation, the segmenting dynamic clustering (SDC) method is proposed, which divides the training process into two phases. Precisely, in the first phases, SDC adopts the single image features in the clustering phase to ensure that accurate feature details can be learned. In the second phase, SDC fuses SIR and CIR as the final feature for clustering to interactively promote the SIR branch and CIR branch. JLIRS-UDA learns the SIR and CIR jointly in the UDA task training phase. Compared with the state-of-the-arts methods, the strategy proposed in this paper has achieved a significant improvement of 7.1% mean average precision (mAP) on the tasks of Market-1501 (Market) to DukeMTMC- Re-ID (Duke). The slightest improvement in accuracy also achieved +0.8% on Market to MSMT17 (MSMT).

References

[1] Xiong L, Tang G. Multi-object tracking based on deep associated features for UAV applications[J]. Optoelectronics letters, 2023, 19(2): 105-111

[2] Yu H X, Zheng W S, Wu A, et al. Unsupervised person re-identification by soft multilabel learning[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15–20, 2019, Long Beach, CA, USA, 2019, New York: IEEE 2148-2157

[3] Li X, Zhang T, Zhao X, et al. Learning fused features with parallel training for person re-identification[J]. Knowledge-based systems, 2021, 220: 106941

[4] Song L, Wang C, Zhang L, et al. Unsupervised domain adaptive re-identification: theory and practice[J]. Pattern recognition, 2020, 102: 107173

[5] Fu Y, Wei Y, Wang G, et al. Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 27-November 2, 2019, Seoul, Korea (South), 2019, New York: IEEE 6112-6121

[6] Yang F, Li K, Zhong Z, et al. Asymmetric co-teaching for unsupervised cross-domain person re-identification[C]. Proceedings of the AAAI Conference on Artificial Intelligence, February 7–12, 2020, New York, NY, USA, 2020 12597-12604 34 (07)

[7] Yu H X, Wu A, Zheng W S. Cross-view asymmetric metric learning for unsupervised person re-identification[C]. Proceedings of the IEEE International Conference on Computer Vision, October 22–29, 2017, Venice, Italy, 2017, New York: IEEE 994-1002

[8] Fan H, Zheng L, Yan C, et al. Unsupervised person re-identification: clustering and fine-tuning[J]. ACM transactions on multimedia computing, communications, and applications (TOMM), 2018, 14(4): 1-18

[9] Han B, Yao Q, Yu X, et al. Co-teaching: robust training of deep neural networks with extremely noisy labels[J]. Advances in neural information processing systems, 2018 31

[10] Ding S, Lin L, Wang G, et al. Deep feature learning with relative distance comparison for person re-identification[J]. Pattern recognition, 2015, 48(10): 2993-3003

[11] Li W, Zhao R, Xiao T, et al. Deepreid: deep filter pairing neural network for person re-identification[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 23–28, 2014, Columbus, OH, USA, 2014, New York: IEEE 152-159

[12] Ahmed E, Jones M, Marks T K. An improved deep learning architecture for person re-identification[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 7–12, 2015, Boston, MA, USA, 2015, New York: IEEE 3908-3916

[13] Wang G, Yuan Y, Chen X, et al. Learning discriminative features with multiple granularities for person re-identification[C]. Proceedings of the 26th ACM International Conference on Multimedia, October 22–26, 2018, Seoul, Korea (South), 2018 274-282

[14] Dai Z, Wang G, Yuan W, et al. Cluster contrast for unsupervised person re-identification[C]. Proceedings of the Asian Conference on Computer Vision, December 4–8, 2022, Macao, China, 2022 1142-1160

[15] Yan Y, Qin J, Ni B, et al. Learning multi-attention context graph for group-based re-identification[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 45(6): 7001-7018

[16] Zhong Z, Zheng L, Li S, et al. Generalizing a person retrieval model hetero-and homogeneously[C]. Proceedings of the European Conference on Computer Vision (ECCV), September 8–14, 2018, Munich, Germany, 2018, Berlin, Heidelberg: Springer-Verlag 172-188

[17] Liu J, Zha Z J, Chen D, et al. Adaptive transfer network for cross-domain person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15–20, 2019, Long Beach, CA, USA, 2019, New York: IEEE 7202-7211

[18] Huang Y, Wu Q, Xu J S, et al. SBSGAN: suppression of inter-domain background shift for person re-identification[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 27–November 2, 2019, Seoul, Korea (South), 2019, New York: IEEE 9527-9536

[19] Qi L, Wang L, Huo J, et al. A novel unsupervised camera-aware domain adaptation framework for person re-identification[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 27–November 2, 2019, Seoul, Korea (South), 2019, New York: IEEE 8080-8089

[20] Zhong Z, Zheng L, Luo Z, et al. Invariance matters: exemplar memory for domain adaptive person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15–20, 2019, Long Beach, CA, USA, 2019, New York: IEEE 598-607

[21] Li Y J, Lin C S, Lin Y B, et al. Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, June 15–20, 2019, Long Beach, CA, USA, 2019, New York: IEEE 7919-7929

[22] Fu Y, Wei Y, Wang G, et al. Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 27-November 2, 2019, Seoul, Korea (South), 2019, New York: IEEE 6112-6121

[23] Zhang X, Cao J, Shen C, et al. Self-training with progressive augmentation for unsupervised cross-domain person re-identification[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, October 27-November 2, 2019, Seoul, Korea (South), 2019, New York: IEEE 8222-8231

[24] Zeng K, Ning M, Wang Y, et al. Hierarchical clustering with hard-batch triplet loss for person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 13–19, 2020, Seattle, WA, USA, 2020, New York: IEEE 13657-13665

[25] Jin X, Lan C, Zeng W, et al. Style normalization and restitution for generalizable person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 13–19, 2020, Seattle, WA, USA, 2020, New York: IEEE 3143-3152

[26] Zhai Y, Ye Q, Lu S, et al. Multiple expert brainstorming for domain adaptive person re-identification[C]. 16th European Conference on Computer Vision, August 23–28, 2020, Glasgow, UK, 2020, Berlin, Heidelberg: Springer-Verlag 594-611

[27] Ge Y, Zhu F, Chen D, et al. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id[J]. Advances in neural information processing systems, 2020, 33: 11309-11321

[28] Bai Z, Wang Z, Wang J, et al. Unsupervised multi-source domain adaptation for person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20–25, 2021, Nashville, TN, USA, 2021, New York: IEEE 12914-12923

[29] Ge Y, Zhu F, Chen D, et al. Structured domain adaptation with online relation regularization for unsupervised person re-id[J]. IEEE transactions on neural networks and learning systems, 2022