Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class Priors
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_ | 1866917781235040256 |
|---|---|
| author | Jiang, Houwang Liu, Zhuxian Liu, Guodong Liu, Xiaolong Zhan, Shihua |
| author_facet | Jiang, Houwang Liu, Zhuxian Liu, Guodong Liu, Xiaolong Zhan, Shihua |
| contents | Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always necessary, and do class labels fully capture the fine-grained features within the data? In this paper, we propose Contrastive Disentangling (CD), a framework designed to learn representations without relying on class priors. CD leverages a multi-level contrastive learning strategy, integrating instance-level and feature-level contrastive losses with a normalized entropy loss to capture semantically rich and fine-grained representations. Specifically, (1) the instance-level contrastive loss separates feature representations across samples; (2) the feature-level contrastive loss promotes independence among feature heads; and (3) the normalized entropy loss ensures feature diversity and prevents feature collapse. Extensive experiments on CIFAR-10, CIFAR-100, STL-10, and ImageNet-10 demonstrate that CD outperforms existing methods in scenarios where class information is unavailable or ambiguous. The code is available at https://github.com/Hoper-J/Contrastive-Disentangling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_04867 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class Priors Jiang, Houwang Liu, Zhuxian Liu, Guodong Liu, Xiaolong Zhan, Shihua Computer Vision and Pattern Recognition Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always necessary, and do class labels fully capture the fine-grained features within the data? In this paper, we propose Contrastive Disentangling (CD), a framework designed to learn representations without relying on class priors. CD leverages a multi-level contrastive learning strategy, integrating instance-level and feature-level contrastive losses with a normalized entropy loss to capture semantically rich and fine-grained representations. Specifically, (1) the instance-level contrastive loss separates feature representations across samples; (2) the feature-level contrastive loss promotes independence among feature heads; and (3) the normalized entropy loss ensures feature diversity and prevents feature collapse. Extensive experiments on CIFAR-10, CIFAR-100, STL-10, and ImageNet-10 demonstrate that CD outperforms existing methods in scenarios where class information is unavailable or ambiguous. The code is available at https://github.com/Hoper-J/Contrastive-Disentangling. |
| title | Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.04867 |