Research map / Vision-language and multimodal / Cross-modal learning
Hyper-Opinion Vagueness Quantification for Robust Multimodal Learning
Disen Hu, Xun Jiang, Xiaofeng Cao, Zheng Wang, Jingkuan Song, Heng Tao Shen, Xing Xu
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 hyper-opinion vagueness quantification and gradient modulation (HOVQ) | ECML · MVSA-Single (Gaussian eps=10.0) | accuracy (%): 61.03 -> 63.34 | Improved |
| use HOVQ instead of EAU | EAU · SUN RGB-D (clean) | accuracy (%): 55.68 -> 62.24 | Improved |
| use HOVQ vs best baseline on clean CREMA-D | MMPareto · CREMA-D (clean) | accuracy (%): 75.13 -> 75.19 | No clear effect |
| use HOVQ vs MMPareto under Gaussian noise | MMPareto · CREMA-D (Gaussian eps=10.0) | accuracy (%): 39.65 -> 63.94 | Improved |
| use HOVQ vs QMF on clean SUN RGB-D | QMF · SUN RGB-D (clean) | accuracy (%): 61.98 -> 62.24 | No clear effect |
| use HOVQ vs CRMT under l2 PGD attack | CRMT · UCF101 | adversarial accuracy: 0.614 -> 0.625 | Improved |
| use HOVQ vs CRMT under l2 PGD attack | CRMT · Kinetics-Sounds | adversarial accuracy: 0.608 -> 0.649 | Improved |
| add Hyper-Opinion Gradient Modulation (ablation) | HOVQ · MVSA-Single (Gaussian noise) | accuracy (%): about 7% drop without it | Improved |
| add unimodal GDD loss L_uni (ablation) | HOVQ · MVSA-Single (Gaussian noise) | accuracy (%) | Improved |
| plug HOGM into ECML (ablation) | ECML · CREMA-D and NYU Depth v2 (noise) | accuracy (%): about +1% | Improved |
| increase number of composites (ablation) | HOVQ · SUN RGB-D (clean, salt-pepper) | accuracy (%) | Improved |
Closest papers by meaning
- Multimodal Negative Learning (NeurIPS 2025 · similarity 0.86)
- Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization (ICLR 2026 · similarity 0.85)
- Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion (CVPR 2024 · similarity 0.85)
- Fusion or Confusion? Multimodal Complexity Is Not All You Need (NeurIPS 2026 · similarity 0.85)
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.85)
- Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty (ICLR 2024 · similarity 0.84)
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.
