Clustering-friendly Representation Learning for Enhancing Salient Features
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909282669166592 |
|---|---|
| author | Oshima, Toshiyuki Takagi, Kentaro Nakata, Kouta |
| author_facet | Oshima, Toshiyuki Takagi, Kentaro Nakata, Kouta |
| contents | Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply unsupervised settings, and definitions of importance vary according to the type of downstream task or analysis goal, such as the identification of objects or backgrounds. In this paper, we focus on unsupervised image clustering as the downstream task and propose a representation learning method that enhances features critical to the clustering task. We extend a clustering-friendly contrastive learning method and incorporate a contrastive analysis approach, which utilizes a reference dataset to separate important features from unimportant ones, into the design of loss functions. Conducting an experimental evaluation of image clustering for three datasets with characteristic backgrounds, we show that for all datasets, our method achieves higher clustering scores compared with conventional contrastive analysis and deep clustering methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04891 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Clustering-friendly Representation Learning for Enhancing Salient Features Oshima, Toshiyuki Takagi, Kentaro Nakata, Kouta Computer Vision and Pattern Recognition Machine Learning Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply unsupervised settings, and definitions of importance vary according to the type of downstream task or analysis goal, such as the identification of objects or backgrounds. In this paper, we focus on unsupervised image clustering as the downstream task and propose a representation learning method that enhances features critical to the clustering task. We extend a clustering-friendly contrastive learning method and incorporate a contrastive analysis approach, which utilizes a reference dataset to separate important features from unimportant ones, into the design of loss functions. Conducting an experimental evaluation of image clustering for three datasets with characteristic backgrounds, we show that for all datasets, our method achieves higher clustering scores compared with conventional contrastive analysis and deep clustering methods. |
| title | Clustering-friendly Representation Learning for Enhancing Salient Features |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2408.04891 |