The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification
Open accessAbstract
Person re-identification (Re-ID) has achieved great improvement with deep learning and a large amount of labelled training data. However, it remains a challenging task for adapting a model trained in a source domain of labelled data to a target domain of only unlabelled data available. In this work, we develop a self-training method with progressive augmentation framework (PAST) to promote the model performance progressively on the target dataset. Specially, our PAST framework consists of two stages, namely, conservative stage and promoting stage. The conservative stage captures the local structure of target-domain data points with triplet-based loss functions, leading to improved feature representations. The promoting stage continuously optimizes the network by appending a changeable classification layer to the last layer of the model, enabling the use of global information about the data distribution. Importantly, we propose a new self-training strategy that progressively augments the model capability by adopting conservative and promoting stages alternately. Furthermore, to improve the reliability of selected triplet samples, we introduce a ranking-based triplet loss in the conservative stage, which is a label-free objective function based on the similarities between data pairs. Experiments demonstrate that the proposed method achieves state-of-the-art person Re-ID performance under the unsupervised cross-domain setting.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Self-citationImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
(1996) · Cited by 20,179
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Scalable Person Re-identification: A Benchmark
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.133 · Cited by 4,506
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 1×
“Since the percentage of corrupted labels largely affect the model generalization on the target dataset [42], we propose a method to improve the quality of labels in a progressive way which results in considerable improvement of model generalization on the unseen target dataset.”
MethodIn Defense of the Triplet Loss for Person Re-Identification
Hermans, A., Beyer, L., & Leibe, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.07737 · Cited by 2,687
Density-Based Clustering Based on Hierarchical Density Estimates
Campello, R. J. G. B., Moulavi, D., & Sander, J. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-37456-2_14 · Cited by 2,680 · cited 17×
“, k-means, DBSCAN [11] and HDBSCAN [3] in the conservative stage.”
MethodInfluentialDeepReID: Deep Filter Pairing Neural Network for Person Re-identification
Li, W., Zhao, R., Xiao, T., & Wang, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.27 · Cited by 2,611
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., & Wang, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_30 · Cited by 2,522
Person Transfer GAN to Bridge Domain Gap for Person Re-identification
Wei, L., Zhang, S., Gao, W., & Tian, Q. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00016 · Cited by 2,118
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro
Zheng, Z., Zheng, L., & Yang, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.405 · Cited by 1,984
Re-ranking Person Re-identification with k-Reciprocal Encoding
Zhong, Z., Zheng, L., Cao, D., & Li, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.389 · Cited by 1,583
Harmonious Attention Network for Person Re-identification
Li, W., Zhu, X., & Gong, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00243 · Cited by 1,449
Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
Cheng, D., Gong, Y., Zhou, S., Wang, J., & Zheng, N. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.149 · Cited by 1,247
Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., & Jiao, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00110 · Cited by 1,011
Evaluating Appearance Models for Recognition, Reacquisition, and Tracking
Gray, D. A., Brennan, S., & Hai, T. (2007) · Cited by 984
SVDNet for Pedestrian Retrieval
Sun, Y., Zheng, L., Deng, W., & Wang, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.410 · Cited by 825
Mask-Guided Contrastive Attention Model for Person Re-identification
Song, C., Huang, Y., Ouyang, W., & Wang, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00129 · Cited by 653
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification
Wang, J., Zhu, X., Gong, S., & Li, W. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00242 · Cited by 637
Unsupervised Person Re-identification: Clustering and Fine-tuning
Fan, H., Zheng, L., Yan, C., & Yang, Y. (2018) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3243316 · Cited by 636
Camera Style Adaptation for Person Re-identification
Zhong, Z., Zheng, L., Zheng, Z., Li, S., & Yang, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00541 · Cited by 635
GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence
Bian, J., Lin, W.-Y., Matsushita, Y., Yeung, S.-K., Nguyen, T.-D., & Cheng, M.-M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.302 · Cited by 594
A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification
Lin, Y., Dong, X., Zheng, L., Yan, Y., & Yang, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018738 · Cited by 564
Multi-level Factorisation Net for Person Re-identification
Chang, X., Hospedales, T. M., & Xiang, T. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00225 · Cited by 550
Attention-Aware Compositional Network for Person Re-identification
Xu, J., Zhao, R., Zhu, F., Wang, H., & Ouyang, W. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00226 · Cited by 502
Generalizing a Person Retrieval Model Hetero- and Homogeneously
Zhong, Z., Zheng, L., Li, S., & Yang, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01261-8_11 · Cited by 498
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
Zhang, X., Luo, H., Fan, X., Xiang, W., Sun, Y., Xiao, Q., Jiang, W., Zhang, C., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1711.08184 · Cited by 419 · cited 1×
“They mainly focus on well-designed model architectures [32, 8, 37, 33, 43, 39, 7, 4], additional attributions [5, 29, 48, 6] and metric learning [14, 17, 23, 46].”
BackgroundSelf-citationUnsupervised Cross-Dataset Transfer Learning for Person Re-identification
Peng, P., Xiang, T., Wang, Y., Pontil, M., Gong, S., Huang, T., & Tian, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.146 · Cited by 416
Person Re-identification by Deep Learning Multi-scale Representations
Chen, Y., Zhu, X., & Gong, S. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.304 · Cited by 415
Learning to rank in person re-identification with metric ensembles
Paisitkriangkrai, S., Shen, C., & van den Hengel, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298794 · Cited by 385
Self-citationUnsupervised domain adaptive re-identification: Theory and practice
Song, L., Wang, C., Zhang, L., Du, B., Zhang, Q., Huang, C., & Wang, X. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107173 · Cited by 376
Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification
Yu, H.-X., Wu, A., & Zheng, W. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.113 · Cited by 342
Person Re-Identification by Iterative Re-Weighted Sparse Ranking
Lisanti, G., Masi, I., Bagdanov, A. D., & Bimbo, A. D. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2369055 · Cited by 299
Person Search via a Mask-Guided Two-Stream CNN Model
Chen, D., Zhang, S., Ouyang, W., Yang, J., & Tai, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_45 · Cited by 230
A Multi-Task Deep Network for Person Re-Identification
Chen, W., Chen, X., Zhang, J., & Huang, K. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11201 · Cited by 198
Lv, J., Chen, W., Li, Q., et al. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00829 · Cited by 196
Deep Transfer Learning for Person Re-identification
Geng, M., Wang, Y., Xiang, T., & Tian, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05244 · Cited by 192
Multi-Region bilinear convolutional neural networks for person re-identification
Ustinova, E., Ganin, Y., & Lempitsky, V. (2017) · 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078460 · Cited by 176
Stepwise Metric Promotion for Unsupervised Video Person Re-identification
Liu, Z., Wang, D., & Lu, H. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.266 · Cited by 175
Li, Y.-J., Yang, F.-E., Liu, Y., Yeh, Y.-Y., Du, X., & Wang, Y.-C. F. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00054 · Cited by 137
Unsupervised Learning of Generative Topic Saliency for Person Re-identification
Wang, H., Gong, S., & Xiang, T. (2014) · British Machine Vision Conference (BMVC) · doi:10.5244/c.28.48 · Cited by 105
An Evaluation of Feature Matchers for Fundamental Matrix EstimationPreprint
Bian, J.-W., Wu, Y.-H., Zhao, J. Y., Liu, Y., Zhang, L., Cheng, M., & Reid, I. D. (2019) · arXiv (Cornell University) · doi:10.5244/c.33.89 · Cited by 70
Towards unsupervised open-set person re-identification
Wang, H., Zhu, X., Xiang, T., & Gong, S. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532461 · Cited by 68
Shen, T., Gong, D., Zhang, W., Shen, C., & Mei, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12282 · Cited by 18
Self-citation
Cited by
Deep Learning for Person Re-Identification: A Survey and Outlook
Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., & Hoi, S. C. H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3054775 · Cited by 2,259
Style Normalization and Restitution for Generalizable Person Re-Identification
Jin, X., Lan, C., Zeng, W., Chen, Z., & Zhang, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00321 · Cited by 426
Unsupervised Person Re-Identification via Multi-Label Classification
Wang, D., & Zhang, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01099 · Cited by 373
Ge, Y., Chen, D., & Li, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01526 · Cited by 370
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
Ge, Y., Zhu, F., Chen, D., Zhao, R., & Li, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02713 · Cited by 329
Metadata
- Authors
- Zhang, X., Cao, J., Shen, C., & You, M.
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 8221-8230
- OpenAlex
- W3009761962
- Cited by
- 267
- References
- 45
- FWCI
- 16.53
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.