Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, Yu-Chiang Frank Wang; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 7919-7929

Abstract


Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. To address this challenging task, existing re-ID models typically rely on a large amount of labeled training data, which is not practical for real-world applications. To alleviate this limitation, researchers now targets at cross-dataset re-ID which focuses on generalizing the discriminative ability to the unlabeled target domain when given a labeled source domain dataset. To achieve this goal, our proposed Pose Disentanglement and Adaptation Network (PDA-Net) aims at learning deep image representation with pose and domain information properly disentangled. With the learned cross-domain pose invariant feature space, our proposed PDA-Net is able to perform pose disentanglement across domains without supervision in identities, and the resulting features can be applied to cross-dataset re-ID. Both of our qualitative and quantitative results on two benchmark datasets confirm the effectiveness of our approach and its superiority over the state-of-the-art cross-dataset Re-ID approaches.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2019_ICCV,
author = {Li, Yu-Jhe and Lin, Ci-Siang and Lin, Yan-Bo and Wang, Yu-Chiang Frank},
title = {Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}