Attention-Aware Adversarial Network for Person Re-Identification
Source abstract
Abstract
Person re-identification (re-ID) is a fundamental problem in the field of computer vision. The performance of deep learning-based person re-ID models suffers from a lack of training data. In this work, we introduce a novel image-specific data augmentation method on the feature map level to enforce feature diversity in the network. Furthermore, an attention assignment mechanism is proposed to enforce that the person re-ID classifier focuses on nearly all important regions of the input person image. To achieve this, a three-stage framework is proposed. First, a baseline classification network is trained for person re-ID. Second, an attention assignment network is proposed based on the baseline network, in which the attention module learns to suppress the response of the current detected regions and re-assign attentions to other important locations. By this means, multiple important regions for classification are highlighted by the attention map. Finally, the attention map is integrated in the attention-aware adversarial network (AAA-Net), which generates high-performance classification results with an adversarial training strategy. We evaluate the proposed method on two large-scale benchmark datasets, including Market1501 and DukeMTMC-reID. Experimental results show that our algorithm performs favorably against the state-of-the-art methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Advanced Neural Network Applications · Face recognition and analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China
Department of Basic Courses, Criminal Investigation Police University of China, Shenyang 110854, China
References (41)
Show source-provided references
1. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). ImageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA.
2. Simonyan, K., and Zisserman, A. (arXiv, 2014). Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv.
3. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
4. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
5. Huang, H., Li, D., Zhang, Z., Chen, X., and Huang, K. (2018, January 18–22). Adversarially Occluded Samples for Person Re-Identification. Proceedings of the the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00535 ↗
6. Zhuo, J., Chen, Z., Lai, J., and Wang, G. (arXiv, 2018). Occluded Person Re-identification, arXiv.10.1109/ICME.2018.8486568 ↗
7. Wang, X., Shrivastava, A., and Gupta, A. (2017, January 22–25). A-fast-rcnn: Hard positive generation via adversary for object detection. Proceedings of the the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.324 ↗
8. Cheng, D., Chang, X., Liu, L., Hauptmann, A.G., Gong, Y., and Zheng, N. (2017, January 19–25). Discriminative Dictionary Learning With Ranking Metric Embedded for Person Re-Identification. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence—IJCAI 2017, Melbourne, Australia.10.24963/ijcai.2017/134 ↗
9. Chen, J., Wang, Y., Qin, J., Liu, L., and Shao, L. (2017, January 21–26). Fast Person Re-identification via Cross-Camera Semantic Binary Transformation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.566 ↗
10. Li, D., Chen, X., Zhang, Z., and Huang, K. (2017, January 21–26). Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.782 ↗
11. Zhao, L., Li, X., Zhuang, Y., and Wang, J. (2017, January 22–29). Deeply-Learned Part-Aligned Representations for Person Re-identification. Proceedings of the IEEE International Conference on Computer Vision—ICCV 2017, Venice, Italy.10.1109/ICCV.2017.349 ↗
12. Deng, W., Zheng, L., Kang, G., Yang, Y., Ye, Q., and Jiao, J. (arXiv, 2017). Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification, arXiv.10.1109/CVPR.2018.00110 ↗
13. Wei, L., Zhang, S., Gao, W., and Tian, Q. (arXiv, 2017). Person Transfer GAN to Bridge Domain Gap for Person Re-Identification, arXiv.10.1109/CVPR.2018.00016 ↗
14. Yao, H., Zhang, S., Zhang, Y., Li, J., and Tian, Q. (arXiv, 2017). Deep Representation Learning with Part Loss for Person Re-Identification, arXiv.
15. Sun, Y., Zheng, L., Deng, W., and Wang, S. (2017, January 22–29). SVDNet for Pedestrian Retrieval. Proceedings of the IEEE International Conference on Computer Vision—ICCV 2017, Venice, Italy.10.1109/ICCV.2017.410 ↗
16. Li, W., Zhu, X., and Gong, S. (2017, January 19–25). Person Re-Identification by Deep Joint Learning of Multi-Loss Classification. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence—IJCAI 2017, Melbourne, Australia.10.24963/ijcai.2017/305 ↗
17. Zhao, H., Tian, M., Sun, S., Shao, J., Yan, J., Yi, S., Wang, X., and Tang, X. (2017, January 21–26). Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.103 ↗
18. Wei, L., Zhang, S., Yao, H., Gao, W., and Tian, Q. (2017, January 23–27). GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval. Proceedings of the 2017 ACM on Multimedia Conference—MM 2017, Mountain View, CA, USA.10.1145/3123266.3123279 ↗
19. Zheng, L., Huang, Y., Lu, H., and Yang, Y. (arXiv, 2017). Pose Invariant Embedding for Deep Person Re-identification, arXiv.
20. Varior, R.R., Haloi, M., and Wang, G. (2016, January 11–14). Gated Siamese Convolutional Neural Network Architecture for Human Re-identification. Proceedings of the Computer Vision—ECCV 2016—14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46484-8_48 ↗
21. Schroff, F., Kalenichenko, D., and Philbin, J. (arXiv, 2015). FaceNet: A Unified Embedding for Face Recognition and Clustering, arXiv.10.1109/CVPR.2015.7298682 ↗
22. Liu, H., Feng, J., Qi, M., Jiang, J., and Yan, S. (arXiv, 2016). End-to-End Comparative Attention Networks for Person Re-identification, arXiv.10.1109/TIP.2017.2700762 ↗
23. Cheng, D., Gong, Y., Zhou, S., Wang, J., and Zheng, N. (2016, January 27–30). Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2016, Las Vegas, NV, USA.10.1109/CVPR.2016.149 ↗
24. Chen, W., Chen, X., Zhang, J., and Huang, K. (2017, January 21–26). Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.145 ↗
25. Mignon, A., and Jurie, F. (2012, January 16–21). PCCA: A new approach for distance learning from sparse pairwise constraints. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6247987 ↗
26. Kai Li, Z.D. (2018, January 2–7). Discriminative Semi-coupled Projective Dictionary Learning for Low-Resolution Person Re-Identification. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LO, USA.10.1609/aaai.v32i1.11908 ↗
27. He, L., Liang, J., Li, H., and Sun, Z. (arXiv, 2018). Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach, arXiv.10.1109/CVPR.2018.00739 ↗
28. Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (arXiv, 2017). Random Erasing Data Augmentation, arXiv.
29. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., and Tian, Q. (2015, January 7–13). Scalable Person Re-identification: A Benchmark. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.133 ↗
30. Zheng, Z., Zheng, L., and Yang, Y. (2017, January 22–29). Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.405 ↗
31. Ristani, E., Solera, F., Zou, R., Cucchiara, R., and Tomasi, C. (2016, January 8–16). Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. Proceedings of the European Conference on Computer Vision workshop on Benchmarking Multi-Target Tracking, Amsterdam, The Netherlands.10.1007/978-3-319-48881-3_2 ↗
32. Jose, C., and Fleuret, F. (2016, January 11–14). Scalable Metric Learning via Weighted Approximate Rank Component Analysis. Proceedings of the Computer Vision—ECCV 2016—14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46454-1_53 ↗
33. Chen, D., Yuan, Z., Chen, B., and Zheng, N. (2016, January 27–30). Similarity Learning with Spatial Constraints for Person Re-identification. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2016, Las Vegas, NV, USA.10.1109/CVPR.2016.142 ↗
34. Zhang, L., Xiang, T., and Gong, S. (2016, January 27–30). Learning a Discriminative Null Space for Person Re-identification. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2016, Las Vegas, NV, USA.10.1109/CVPR.2016.139 ↗
35. Zhou, S., Wang, J., Wang, J., Gong, Y., and Zheng, N. (2017, January 21–26). Point to Set Similarity Based Deep Feature Learning for Person Re-Identification. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.534 ↗
36. Person Re-Identification by Camera Correlation Aware Feature Augmentation10.1109/TPAMI.2017.2666805 ↗
37. Lin, J., Ren, L., Lu, J., Feng, J., and Zhou, J. (2017, January 21–26). Consistent-Aware Deep Learning for Person Re-identification in a Camera Network. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, Honolulu, HI, USA.10.1109/CVPR.2017.362 ↗
38. Xiao, T., Li, S., Wang, B., Lin, L., and Wang, X. (arXiv, 2016). End-to-End Deep Learning for Person Search, arXiv.
39. Schumann, A., and Stiefelhagen, R. (2017, January 21–26). Person Re-identification by Deep Learning Attribute-Complementary Information. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.10.1109/CVPRW.2017.186 ↗
40. Zheng, Z., Zheng, L., and Yang, Y. (arXiv, 2017). Pedestrian Alignment Network for Large-scale Person Re-identification, arXiv.
41. Lin, Y., Zheng, L., Zheng, Z., Wu, Y., and Yang, Y. (arXiv, 2017). Improving Person Re-identification by Attribute and Identity Learning, arXiv.