Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID

14 Mar 2020  ·  Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Xiaogang Wang, Hongsheng Li ·

Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to an unlabeled target-domain dataset. The task of UDA on open-set person re-identification (re-ID) is even more challenging as the identities (classes) do not have overlap between the two domains. One major research direction was based on domain translation, which, however, has fallen out of favor in recent years due to inferior performance compared to pseudo-label-based methods. We argue that the domain translation has great potential on exploiting the valuable source-domain data but existing methods did not provide proper regularization on the translation process. Specifically, previous methods only focus on maintaining the identities of the translated images while ignoring the inter-sample relations during translation. To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term. During training, the person feature encoder is optimized to model inter-sample relations on-the-fly for supervising relation-consistency domain translation, which in turn, improves the encoder with informative translated images. The encoder can be further improved with pseudo labels, where the source-to-target translated images with ground-truth identities and target-domain images with pseudo identities are jointly used for training. In the experiments, our proposed framework is shown to achieve state-of-the-art performance on multiple UDA tasks of person re-ID. With the synthetic-to-real translated images from our structured domain-translation network, we achieved second place in the Visual Domain Adaptation Challenge (VisDA) in 2020.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Unsupervised Domain Adaptation Duke to Market SDA mAP 70.0 # 7
rank-1 86.9 # 6
rank-5 94.4 # 5
rank-10 96.3 # 6
Unsupervised Domain Adaptation Duke to MSMT SDA mAP 25.6 # 4
rank-1 54.4 # 3
rank-5 66.4 # 3
rank-10 71.3 # 3
Unsupervised Domain Adaptation Market to Duke SDA mAP 61.4 # 7
rank-1 76.5 # 6
rank-5 86.6 # 5
rank-10 89.7 # 5
Unsupervised Domain Adaptation Market to MSMT SDA mAP 23.2 # 4
rank-1 49.5 # 4
rank-5 62.2 # 5
rank-10 67.7 # 5

Methods


No methods listed for this paper. Add relevant methods here