Research map / Vision-language and multimodal / Cross-modal learning
Semi-Supervised Multi-Modal Learning with Balanced Spectral Decomposition
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 |
|---|---|---|---|
| use balanced eigenvalue-based loss instead of directly optimizing the ratio trace loss (ablation) | SMLN · XMediaNet 5% labeled | mAP (avg): 0.009 -> 0.612 | Helped |
| use balanced eigenvalue-based loss instead of lower-bound eigenvalue maximization (ablation) | SMLN · XMediaNet 5% labeled | mAP (avg): 0.579 -> 0.612 | Helped |
| use balanced eigenvalue-based loss instead of lower-bound eigenvalue maximization (ablation) | SMLN · XMediaNet 30% labeled | mAP (avg): 0.583 -> 0.620 | Helped |
| add intra-modal geometric structure (ablation) | SMLN · XMediaNet 5% labeled | mAP (avg): 0.583 -> 0.612 | Helped |
| add intra-modal geometric structure (ablation) | SMLN · XMediaNet 30% labeled | mAP (avg): 0.599 -> 0.620 | Helped |
Closest papers by meaning
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data (ICLR 2024 · similarity 0.86)
- Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval (CVPR 2024 · similarity 0.85)
- Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval (CVPR 2025 · similarity 0.85)
- Semi-Supervised Multimodal Classification Through Learning from Modal and Strategic Complementarities (AAAI 2025 · similarity 0.85)
- DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval (AAAI 2025 · similarity 0.85)
- RedCore: Relative Advantage Aware Cross-Modal Representation Learning for Missing Modalities with Imbalanced Missing Rates (AAAI 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.