Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
Ranking
Overall
58
Content
65
Popularity
41
Observed public metrics from 1 member.
Merged summary
TL;DR - This paper introduces two co-learning methods for multimodal classification when arbitrary subsets of modalities may be unavailable at inference. The approaches improve robustness by emphasizing cross-modal collaboration at the feature and decision levels rather than relying primarily on fusion.
- Supports unspecified missing-modality patterns beyond typical bimodal settings.
- One method is more robust when only one modality is missing.
- The other performs better when all but one modality are missing.
- Experiments on two benchmarks show significant robustness gains across missing-modality conditions.
Sources (1)
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - This paper introduces two co-learning methods for multimodal classification when arbitrary subsets of modalities may be unavailable at inference. The approaches improve robustness by emphasizing cross-modal collaboration at the feature and decision levels rather than relying primarily on fusion.
- Supports unspecified missing-modality patterns beyond typical bimodal settings.
- One method is more robust when only one modality is missing.
- The other performs better when all but one modality are missing.
- Experiments on two benchmarks show significant robustness gains across missing-modality conditions.