Research map / Vision-language and multimodal / Cross-modal learning
Interest-driven Deep Multi-modal Clustering
Guoliang Zou, Tongji Chen, Sijia Li, Jin Qin, Yangdong Ye, Shizhe Hu
Read the paperCheck your idea against 137,217 papers
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 interest-weighted reconstruction loss (ablation) | IDMC · Caltech2M | ACC: 0.647 -> 0.666 | Improved |
| add interest-weighted reconstruction loss (ablation) | IDMC · Crosstask | ACC: 0.605 -> 0.634 | Improved |
| add interest-weighted alignment loss (ablation) | IDMC · Caltech2M | ACC: 0.601 -> 0.666 | Improved |
| add interest-weighted alignment loss (ablation) | IDMC · Crosstask | ACC: 0.478 -> 0.634 | Improved |
| add interest-weighted KL clustering loss (ablation) | IDMC · Caltech2M | ACC: 0.596 -> 0.666 | Improved |
| add interest-weighted KL clustering loss (ablation) | IDMC · Crosstask | ACC: 0.563 -> 0.634 | Improved |
| add DDC loss (ablation) | IDMC · Caltech2M | ACC: 0.239 -> 0.666 | Improved |
| add DDC loss (ablation) | IDMC · Crosstask | ACC: 0.218 -> 0.634 | Improved |
| add DDC loss (ablation) | IDMC · MIRFlickr | ACC: 0.176 -> 0.579 | Improved |
| add interest value weighting (ablation) | IDMC · Crosstask, Captions | clustering accuracy | Improved |
| use adaptive Bayesian fusion instead of average fusion (ablation) | IDMC · Crosstask, Captions | clustering accuracy | Improved |
| add interest-weighted reconstruction loss (ablation) | IDMC · Captions | ACC: 0.781 -> 0.800 | Improved |
Closest papers by meaning
- Multi-aspect Self-guided Deep Information Bottleneck for Multi-modal Clustering (AAAI 2025 · similarity 0.88)
- A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method (ICML 2025 · similarity 0.87)
- Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering (CVPR 2024 · similarity 0.86)
- Super Deep Contrastive Information Bottleneck for Multi-modal Clustering (ICML 2025 · similarity 0.85)
- Interactive Deep Clustering via Value Mining (NeurIPS 2024 · similarity 0.85)
- Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs (AAAI 2025 · 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.
