Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification

By Yang Fu, Yunchao Wei, Guanshuo Wang, Xi Zhou, Humphrey Shi, Thomas S. Huang. IEEE International Conference on Computer Vision, 2018

477 citations recorded by the source corpus.

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the similar natural characteristics existing in the samples from the target domain for learning to conduct person re-ID in an unsupervised manner. Concretely, we propose a Self-similarity Grouping (SSG) approach, which exploits the potential similarity (from the global body to local parts) of unlabeled samples to build multiple clusters from different views automatically. These independent clusters are then assigned with labels, which serve as the pseudo identities to supervise the training process. We repeatedly and alternatively conduct such a grouping and training process until the model is stable. Despite the apparent simplify, our SSG outperforms the state-of-the-arts by more than 4.6% (DukeMTMC→Market1501) and 4.4% (Market1501→DukeMTMC) in mAP, respectively. Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i.e. the number of independent identities from the target domain is unknown). Without spending much effort on labeling, our SSG ++ can further promote the mAP upon SSG by 10.7% and 6.9%, respectively. Our Code is available at: https://github.com/OasisYang/SSG .

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e095b62847324a4b48c4457f990a07ce6b85f641

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Xiaogang Wang
3. Hongsheng Li
4. Dacheng Tao
5. Luc Van Gool
6. Tao Mei
7. Jiebo Luo
8. Qi Tian

Citations in the corpus

• Style Normalization and Restitution for Generalizable Person Re-Identification (2020, unknown): “4 SSG [6] ICCV’19 Market1501 + Duke (U) 53.”
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (2020, methodology): “(3) Our method significantly outperforms stateof-the-arts [9, 50, 47, 51, 42] on multiple domain adaptation tasks of object re-ID with up to 7.”
• Unsupervised Person Re-Identification via Multi-Label Classification (2020, methodology): “, PTGAN [31], ECN [46], and SSG [7].”
• Cluster Contrast for Unsupervised Person Re-Identification (2021, methodology): “The second category is pure unsupervised learning person re-ID [14,15,30,4,49,57,65,62], which trains model directory on unlabeled dataset.”
• Group-aware Label Transfer for Domain Adaptive Person Re-identification (2021, methodology): “Specifically, we surpass the clusteringbased SSG [42] by considerable margins of 21.”