Research map / Vision-language and multimodal / Cross-modal learning
DM2C: Deep Mixed-Modal Clustering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 cross-modal unifying transformation after adversarial training (ablation) | DM2C · Wikipedia | Accuracy: 0.2395 -> 0.2720 | Helped |
| add cross-modal unifying transformation after adversarial training (ablation) | DM2C · NUS-WIDE-10K | Accuracy: 0.2884 -> 0.3300 | Helped |
| add cross-modal unifying transformation (ablation) | DM2C · Wikipedia | NMI: 0.1311 -> 0.1543 | Helped |
| add cross-modal unifying transformation (ablation) | DM2C · NUS-WIDE-10K | NMI: 0.0672 -> 0.0951 | Helped |
| add adversarial training only (no unifying) (ablation) | DM2C latent features + k-means · Wikipedia | Accuracy: 0.2301 -> 0.2395 | No clear effect |
| add adversarial training only (no unifying) (ablation) | DM2C latent features + k-means · NUS-WIDE-10K | Accuracy: 0.2696 -> 0.2884 | Helped |
| add adversarial training only (no unifying) (ablation) | DM2C latent features + k-means · Wikipedia | ARI: 0.0340 -> 0.0290 | Hurt |
| use DM2C instead of IMSAT | clustering · Wikipedia | Accuracy: 0.2521 -> 0.2720 | Helped |
| use DM2C instead of IMSAT | clustering · Wikipedia | ARI: 0.0573 -> 0.0558 | Hurt |
| use DM2C instead of best baseline | clustering · NUS-WIDE-10K | F-score: 0.3422 -> 0.3043 | Hurt |
| use DM2C instead of DCN | clustering · NUS-WIDE-10K | Accuracy: 0.3036 -> 0.3300 | Helped |
| use deep clustering (DKM, DCN) instead of k-means | clustering · Wikipedia | Accuracy: 0.2291 -> 0.2215 (DCN) | No clear effect |
Closest papers by meaning
- Multi-aspect Self-guided Deep Information Bottleneck for Multi-modal Clustering (AAAI 2025 · similarity 0.87)
- Super Deep Contrastive Information Bottleneck for Multi-modal Clustering (ICML 2025 · similarity 0.87)
- A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method (ICML 2025 · similarity 0.86)
- Multi-Level Cross-Modal Alignment for Image Clustering (AAAI 2024 · similarity 0.86)
- Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering (CVPR 2024 · similarity 0.86)
- Cross-modal Representation Flattening for Multi-modal Domain Generalization (NeurIPS 2024 · similarity 0.85)
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.