From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911271908016128 |
|---|---|
| author | Wang, Likai Han, Ruize Feng, Wei Wang, Song |
| author_facet | Wang, Likai Han, Ruize Feng, Wei Wang, Song |
| contents | Gait recognition is an important AI task, which has been progressed rapidly with the development of deep learning. However, existing learning based gait recognition methods mainly focus on the single domain, especially the constrained laboratory environment. In this paper, we study a new problem of unsupervised domain adaptive gait recognition (UDA-GR), that learns a gait identifier with supervised labels from the indoor scenes (source domain), and is applied to the outdoor wild scenes (target domain). For this purpose, we develop an uncertainty estimation and regularization based UDA-GR method. Specifically, we investigate the characteristic of gaits in the indoor and outdoor scenes, for estimating the gait sample uncertainty, which is used in the unsupervised fine-tuning on the target domain to alleviate the noises of the pseudo labels. We also establish a new benchmark for the proposed problem, experimental results on which show the effectiveness of the proposed method. We will release the benchmark and source code in this work to the public. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_11155 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition Wang, Likai Han, Ruize Feng, Wei Wang, Song Computer Vision and Pattern Recognition Gait recognition is an important AI task, which has been progressed rapidly with the development of deep learning. However, existing learning based gait recognition methods mainly focus on the single domain, especially the constrained laboratory environment. In this paper, we study a new problem of unsupervised domain adaptive gait recognition (UDA-GR), that learns a gait identifier with supervised labels from the indoor scenes (source domain), and is applied to the outdoor wild scenes (target domain). For this purpose, we develop an uncertainty estimation and regularization based UDA-GR method. Specifically, we investigate the characteristic of gaits in the indoor and outdoor scenes, for estimating the gait sample uncertainty, which is used in the unsupervised fine-tuning on the target domain to alleviate the noises of the pseudo labels. We also establish a new benchmark for the proposed problem, experimental results on which show the effectiveness of the proposed method. We will release the benchmark and source code in this work to the public. |
| title | From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2211.11155 |