Research map / Vision-language and multimodal / Cross-modal learning
Multimodal Nested Learning for Decoupled and Coordinated Optimization
Yanglin Feng, Yang Qin, Dezhong Peng, Rui Wang, Xiaomin Song, Peng 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 nested learning structure (vs flat joint optimization) (ablation) | MoNet · CREMA-D | fusion accuracy: 63.26 -> 83.11 | Improved |
| add different update frequencies (vs ff = fs = 1) (ablation) | MoNet · CREMA-D | fusion accuracy: 81.59 -> 83.11 | Improved |
| add outer-layer DMSM (ablation) | MoNet · CREMA-D | fusion accuracy: 31.14 -> 83.11 | Improved |
| add inner-layer AMCF (ablation) | MoNet · CREMA-D | fusion accuracy: 79.40 -> 83.11 | Improved |
| add CCMS in AMCF (ablation) | MoNet · CREMA-D | fusion accuracy: 81.42 -> 83.11 | Improved |
| add EMA in AMCF (ablation) | MoNet · CREMA-D | fusion accuracy: 82.17 -> 83.11 | Improved |
| add AMCF fusion coordination (ablation) | MoNet · CREMA-D | unimodal accuracy: Audio 61.88 -> 59.86 | Mixed |
| use MoNet vs best baseline DGL | MoNet vs DGL · CREMA-D | fusion accuracy: 79.40 -> 83.11 | Improved |
| use MoNet vs ARL | MoNet vs ARL · VGGSound50 | fusion accuracy: 60.19 -> 60.90 | Improved |
| use MoNet vs InfoReg | MoNet vs InfoReg · MVSA | fusion accuracy: 74.05 -> 74.25 | No clear effect |
| use MoNet vs MMPareto | MoNet vs MMPareto · ModelNet | fusion accuracy: 91.60 -> 92.50 | Improved |
Closest papers by meaning
- Multimodal Representation Learning by Alternating Unimodal Adaptation (CVPR 2024 · similarity 0.87)
- Asymmetric Reinforcing Against Multi-Modal Representation Bias (AAAI 2025 · similarity 0.86)
- Balancing Multimodal Training Through Game-Theoretic Regularization (NeurIPS 2025 · similarity 0.86)
- Nested Learning: The Illusion of Deep Learning Architectures (NeurIPS 2025 · similarity 0.85)
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning (NeurIPS 2025 · similarity 0.85)
- Improving Multimodal Learning Balance and Sufficiency through Data Remixing (ICML 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.
