Research map / Vision-language and multimodal / Cross-modal learning
PLUM-Net: Prototype-Induced Label Structuring for Disentangled Multimodal Representation Network
Kehan Wang, Huan Zhao, Yong Wei, Xupeng Zha, Guanghui Ye, Cheng Zhu, Yiming Liu, Zixing Zhang
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 Multilevel Semantic Alignment (MSA) (ablation) | PLUM-Net baseline · CMU-MOSI | ACC-2 (second value): 86.2 -> 88.4 | Improved |
| add Prototype-based Single-modal Label Generation with Task-conditioned Feature Bifurcator (ablation) | PLUM-Net with MSA · CMU-MOSI | ACC-2 (second value): 88.4 -> 89.9 | Improved |
| add Private Refinement module (ablation) | PLUM-Net with MSA, PSL and TFB · CMU-MOSI | ACC-2 (second value): 89.9 -> 90.3 | Improved |
| add all four modules versus baseline (ablation) | PLUM-Net · CMU-MOSI | ACC-2 and F1: 86.2 -> 90.3 ACC-2 | Improved |
| add Multilevel Semantic Alignment to private branch (ablation) | PLUM-Net private branch · CMU-MOSI | t-SNE feature coherence | Improved |
| omit explicit alignment module in common branch (ablation) | common branch · CMU-MOSI | cross-modal cosine similarity | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GLoMo — GLoMo: Unsupervised Learning of Transferable Relational Graphs (NeurIPS 2018) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities (NeurIPS 2026 · similarity 0.87)
- Gramian Multimodal Representation Learning and Alignment (ICLR 2025 · similarity 0.87)
- An Information Criterion for Controlled Disentanglement of Multimodal Data (ICLR 2025 · similarity 0.87)
- MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data (NeurIPS 2026 · similarity 0.86)
- UNIALIGN: Scaling Multimodal Alignment within One Unified Model (CVPR 2025 · similarity 0.86)
- Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization (NeurIPS 2026 · similarity 0.86)
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.
