Research map / Learning theory and algorithms / Clustering
Deep Multiview Clustering by Contrasting Cluster Assignments
Jie Chen, Hua Mao, Wai Lok Woo, Xi Peng
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add pretraining autoencoder stage before fine-tuning (ablation) | CVCL · MSRC-v1 | ACC: 82.38 -> 97.62 | Improved |
| add pretraining stage on large datasets (ablation) | CVCL · Fashion | ACC: 99.16 -> 99.31 | No clear effect |
| add pretraining stage on BDGP (ablation) | CVCL · BDGP | ACC: 99.12 -> 99.2 | No clear effect |
| add regularization term L_a against collapse (ablation) | CVCL · MSRC-v1 | ACC: 55.34 -> 97.62 | Improved |
| add regularization term L_a (ablation) | CVCL · MNIST-USPS | ACC: 59.84 -> 99.7 | Improved |
| add regularization term L_a (ablation) | CVCL · Scene-15 | ACC: 25.04 -> 44.59 | Improved |
| add regularization term L_a (ablation) | CVCL · Fashion | ACC: 99.2 -> 99.31 | No clear effect |
| cluster-level contrast of cluster assignments versus other contrastive MVC methods | DSMVC, DCP, DSIMVC, MFL · MSRC-v1 | ACC: 93.33 -> 97.62 | Improved |
| cluster-level contrast versus ASR on small COIL-20 | ASR · COIL-20 | ACC: 80.9 -> 84.65 | Improved |
| vary alpha and beta loss weights | CVCL · MSRC-v1 vs Fashion | ACC | Mixed |
Closest papers by meaning
- Multi-Level Feature Learning for Contrastive Multi-View Clustering (CVPR 2022 · similarity 0.90)
- EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering (CVPR 2025 · similarity 0.90)
- Balanced Multi-View Clustering (TPAMI 2026 · similarity 0.90)
- Mixture of Experts as Representation Learner for Deep Multi-View Clustering (AAAI 2025 · similarity 0.88)
- Incomplete Contrastive Multi-View Clustering with High-Confidence Guiding (AAAI 2024 · similarity 0.88)
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
