Contrastive Mean-Shift Learning for Generalized Category Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910410100178944 |
|---|---|
| author | Choi, Sua Kang, Dahyun Cho, Minsu |
| author_facet | Choi, Sua Kang, Dahyun Cho, Minsu |
| contents | We address the problem of generalized category discovery (GCD) that aims to partition a partially labeled collection of images; only a small part of the collection is labeled and the total number of target classes is unknown. To address this generalized image clustering problem, we revisit the mean-shift algorithm, i.e., a classic, powerful technique for mode seeking, and incorporate it into a contrastive learning framework. The proposed method, dubbed Contrastive Mean-Shift (CMS) learning, trains an image encoder to produce representations with better clustering properties by an iterative process of mean shift and contrastive update. Experiments demonstrate that our method, both in settings with and without the total number of clusters being known, achieves state-of-the-art performance on six public GCD benchmarks without bells and whistles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09451 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive Mean-Shift Learning for Generalized Category Discovery Choi, Sua Kang, Dahyun Cho, Minsu Computer Vision and Pattern Recognition We address the problem of generalized category discovery (GCD) that aims to partition a partially labeled collection of images; only a small part of the collection is labeled and the total number of target classes is unknown. To address this generalized image clustering problem, we revisit the mean-shift algorithm, i.e., a classic, powerful technique for mode seeking, and incorporate it into a contrastive learning framework. The proposed method, dubbed Contrastive Mean-Shift (CMS) learning, trains an image encoder to produce representations with better clustering properties by an iterative process of mean shift and contrastive update. Experiments demonstrate that our method, both in settings with and without the total number of clusters being known, achieves state-of-the-art performance on six public GCD benchmarks without bells and whistles. |
| title | Contrastive Mean-Shift Learning for Generalized Category Discovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.09451 |