Deep Contrastive Multi-view Clustering under Semantic Feature Guidance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911792459939840 |
|---|---|
| author | Liu, Siwen Liu, Jinyan Yuan, Hanning Li, Qi Geng, Jing Yuan, Ziqiang Han, Huaxu |
| author_facet | Liu, Siwen Liu, Jinyan Yuan, Hanning Li, Qi Geng, Jing Yuan, Ziqiang Han, Huaxu |
| contents | Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting the performance of existing algorithms from further improvement. To solve this problem, we propose a multi-view clustering framework named Deep Contrastive Multi-view Clustering under Semantic feature guidance (DCMCS) to alleviate the influence of false negative pairs. Specifically, view-specific features are firstly extracted from raw features and fused to obtain fusion view features according to view importance. To mitigate the interference of view-private information, specific view and fusion view semantic features are learned by cluster-level contrastive learning and concatenated to measure the semantic similarity of instances. By minimizing instance-level contrastive loss weighted by semantic similarity, DCMCS adaptively weakens contrastive leaning between false negative pairs. Experimental results on several public datasets demonstrate the proposed framework outperforms the state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05768 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Contrastive Multi-view Clustering under Semantic Feature Guidance Liu, Siwen Liu, Jinyan Yuan, Hanning Li, Qi Geng, Jing Yuan, Ziqiang Han, Huaxu Computer Vision and Pattern Recognition Multimedia Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting the performance of existing algorithms from further improvement. To solve this problem, we propose a multi-view clustering framework named Deep Contrastive Multi-view Clustering under Semantic feature guidance (DCMCS) to alleviate the influence of false negative pairs. Specifically, view-specific features are firstly extracted from raw features and fused to obtain fusion view features according to view importance. To mitigate the interference of view-private information, specific view and fusion view semantic features are learned by cluster-level contrastive learning and concatenated to measure the semantic similarity of instances. By minimizing instance-level contrastive loss weighted by semantic similarity, DCMCS adaptively weakens contrastive leaning between false negative pairs. Experimental results on several public datasets demonstrate the proposed framework outperforms the state-of-the-art methods. |
| title | Deep Contrastive Multi-view Clustering under Semantic Feature Guidance |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2403.05768 |