Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2111.14290 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909649323687936 |
|---|---|
| author | Yan, Yichao Li, Junjie Liao, Shengcai Qin, Jie Ni, Bingbing Yang, Xiaokang |
| author_facet | Yan, Yichao Li, Junjie Liao, Shengcai Qin, Jie Ni, Bingbing Yang, Xiaokang |
| contents | Domain generalizable person re-identification aims to apply a trained model to unseen domains. Prior works either combine the data in all the training domains to capture domain-invariant features, or adopt a mixture of experts to investigate domain-specific information. In this work, we argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. To this end, we design a novel framework, which we name two-stream adaptive learning (TAL), to simultaneously model these two kinds of information. Specifically, a domain-specific stream is proposed to capture training domain statistics with batch normalization (BN) parameters, while an adaptive matching layer is designed to dynamically aggregate domain-level information. In the meantime, we design an adaptive BN layer in the domain-invariant stream, to approximate the statistics of various unseen domains. These two streams work adaptively and collaboratively to learn generalizable re-id features. Our framework can be applied to both single-source and multi-source domain generalization tasks, where experimental results show that our framework notably outperforms the state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2111_14290 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification Yan, Yichao Li, Junjie Liao, Shengcai Qin, Jie Ni, Bingbing Yang, Xiaokang Computer Vision and Pattern Recognition Domain generalizable person re-identification aims to apply a trained model to unseen domains. Prior works either combine the data in all the training domains to capture domain-invariant features, or adopt a mixture of experts to investigate domain-specific information. In this work, we argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. To this end, we design a novel framework, which we name two-stream adaptive learning (TAL), to simultaneously model these two kinds of information. Specifically, a domain-specific stream is proposed to capture training domain statistics with batch normalization (BN) parameters, while an adaptive matching layer is designed to dynamically aggregate domain-level information. In the meantime, we design an adaptive BN layer in the domain-invariant stream, to approximate the statistics of various unseen domains. These two streams work adaptively and collaboratively to learn generalizable re-id features. Our framework can be applied to both single-source and multi-source domain generalization tasks, where experimental results show that our framework notably outperforms the state-of-the-art methods. |
| title | TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2111.14290 |