Abstract
Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Existing fully supervised person ReID methods usually suffer from poor generalization capability caused by domain gaps. Unsupervised person ReID has attracted a lot of attention recently, because it works without intensive manual annotation and thus shows great potential in adapting to new conditions. Representation learning plays a critical role in unsupervised person ReID. In this work, we propose a novel selective contrastive learning framework for fully unsupervised feature learning. Specifically, different from traditional contrastive learning strategies, we propose to use multiple positives and adaptively selected negatives for defining the contrastive loss, enabling to learn a feature embedding model with stronger identity discriminative representation. Moreover, we propose to jointly leverage global and local features to construct three dynamic memory banks, among which the global and local ones are used for pairwise similarity computation and the mixture memory bank are used for contrastive loss definition. Experimental results demonstrate the superiority of our method in unsupervised person ReID compared with the state of the art. Our code is available at https://github.com/pangbo1997/Unsup_ReID.git.
- [1] . 2021. Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence. Early access, January 26, 2021.Google Scholar
Cross Ref
- [2] . 2018. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2275–2284.Google Scholar
Cross Ref
- [3] . 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 994–1003.Google Scholar
Cross Ref
- [4] . 2019. Adaptive transfer network for cross-domain person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7202–7211.Google Scholar
Cross Ref
- [5] . 2020. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID. In Advances in Neural Information Processing Systems.Google Scholar
- [6] . 2019. A bottom-up clustering approach to unsupervised person re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 8738–8745. Google Scholar
Digital Library
- [7] . 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10981–10990.Google Scholar
Digital Library
- [8] . 2020. Unsupervised person re-identification via softened similarity learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3390–3399.Google Scholar
Cross Ref
- [9] . 2020. A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709.Google Scholar
- [10] . 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9729–9738.Google Scholar
Cross Ref
- [11] . 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European Conference on Computer Vision (ECCV’18). 480–496.Google Scholar
Digital Library
- [12] . 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15). 3431–3440.Google Scholar
Cross Ref
- [13] . 2017. Deeply-learned part-aligned representations for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 3219–3228.Google Scholar
Cross Ref
- [14] . 2020. Style normalization and restitution for generalizable person re-identification. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20). 3140–3149.Google Scholar
Cross Ref
- [15] . 2020. Tracklet self-supervised learning for unsupervised person re-identification. Proceedings of the AAAI Conference on Artificial Intelligence 34, 7 (2020), 12362–12369.Google Scholar
Cross Ref
- [16] . 2018. Generalizing a person retrieval model hetero-and homogeneously. In Proceedings of the European Conference on Computer Vision (ECCV’18). 172–188.Google Scholar
Cross Ref
- [17] . 2018. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’18).Google Scholar
Cross Ref
- [18] . 2019. Progressive learning for person re-identification with one example. IEEE Transactions on Image Processing. Early access, January 10, 2019.Google Scholar
Cross Ref
- [19] . 2018. Robust anchor embedding for unsupervised video person re-identification in the wild. In Proceedings of the European Conference on Computer Vision (ECCV’18). 170–186.Google Scholar
Cross Ref
- [20] . 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2197–2206.Google Scholar
Cross Ref
- [21] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision. 1116–1124. Google Scholar
Digital Library
- [22] . 2018. Unsupervised representation learning by predicting image rotations. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [23] . 2018. Unsupervised feature learning via non-parametric instance-level discrimination. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- [24] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV’15). 1116–1124. Google Scholar
Digital Library
- [25] . 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Computer Vision Workshop on Benchmarking Multi-Target Tracking.Google Scholar
Cross Ref
- [26] . 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- [27] . 2018. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5177–5186.Google Scholar
Cross Ref
- [28] . 2016. MARS: A video benchmark for large-scale person re-identification. In Computer Vision—ECCV 2016, , , , and (Eds.). Springer International, Cham, Switzerland, 868–884.Google Scholar
- [29] . 2019. Dispersion based clustering for unsupervised person re-identification. In Proceedings of the British Machine Vision Conference (BMVC’19). 264.Google Scholar
- [30] . 2020. Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
- [31] . 2019. Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification. In Proceedings of the 2019 International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [32] . 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20). 10981–10990.Google Scholar
Cross Ref
- [33] . 2018. Deep association learning for unsupervised video person re-identification. arXiv preprint arXiv:1808.07301.Google Scholar
- [34] . 2018. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5177–5186.Google Scholar
Cross Ref
Index Terms
Fully Unsupervised Person Re-Identification via Selective Contrastive Learning
Recommendations
Unsupervised Person Re-Identification via Multi-Label Classification
AbstractThe challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. Most of previous works predict single-class pseudo labels through clustering. To improve the quality of generated pseudo ...
Reliability modeling and contrastive learning for unsupervised person re-identification
AbstractUnsupervised person re-identification (ReID) aims to learn discriminative identity features in scenarios without a ground-truth. Fully unsupervised person ReID methods usually iterate between pseudo-labels prediction and representation ...
Unsupervised Person Re-identification with Multi-Level Feature Contrastive Learning
CNIOT '23: Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of ThingsUnsupervised person re-identification works mainly rely on feature representation learning. In recent years, many methods have used pseudo-labels generated from clustering and applied contrast learning techniques to train models. However, the existing ...






Comments