Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification

Guangcong Wang, Jian-Huang Lai, Wenqi Liang, Guangrun Wang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Most of the existing person re-identification (re-ID) methods achieve promising accuracy in a supervised manner, but they assume the identity labels of the target domain is available. This greatly limits the scalability of person re-ID in real-world scenarios. Therefore, the current person re-ID community focuses on the cross-domain person re-ID that aims to transfer the knowledge from a labeled source domain to an unlabeled target domain and exploits the specific knowledge from the data
more » ... ution of the target domain to further improve the performance. To reduce the gap between the source and target domains, we propose a Smoothing Adversarial Domain Attack (SADA) approach that guides the source domain images to align the target domain images by using a trained camera classifier. To stabilize a memory trace of cross-domain knowledge transfer after its initial acquisition from the source domain, we propose a p-Memory Reconsolidation (pMR) method that reconsolidates the source knowledge with a small probability p during the self-training of the target domain. With both SADA and pMR, the proposed method significantly improves the cross-domain person re-ID. Extensive experiments on Market-1501 and DukeMTMC-reID benchmarks show that our pMR-SADA outperforms all of the state-ofthe-arts by a large margin.
doi:10.1109/cvpr42600.2020.01058 dblp:conf/cvpr/WangLLW20 fatcat:z37bb6thefgkrfbrsapsyzbjfu