AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization

Xiaohan Wang, Zhangtao Cheng, Ting Zhong, Leiting Chen, Fan Zhou

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
add EMA to the multi-modal baseline (ablation)ERM · EPIC-Kitchens flow+audiotop-1 accuracy (%): 56.47 -> 60.94Improved
add AMD, GCC and distillation loss on top of EMA (ablation)MBCD · EPIC-Kitchens flow+audiotop-1 accuracy (%): 60.94 -> 63.08Improved
use adaptive modality dropout instead of none (ablation)MBCD · HAC flow+audiotop-1 accuracy (%): 57.43 -> 59.48Improved
use adaptive instead of fixed (0.5) modality dropout (ablation)MBCD · HAC flow+audiotop-1 accuracy (%): 58.88 -> 59.48Improved
use fixed 0.5 dropout instead of none (ablation)MBCD · HAC flow+audiotop-1 accuracy (%): 57.43 -> 58.88Improved
replace CMRF with MBCDCMRF · EPIC-Kitchens video+audio+flowtop-1 accuracy (%): 65.47 -> 67.58Improved
replace CMRF with MBCDCMRF · HAC video+audio+flowtop-1 accuracy (%): 70.64 -> 71.62Improved
replace CMRF with MBCDCMRF · HAC flow+audiotop-1 accuracy (%): 57.74 -> 59.48Improved
replace CMRF with MBCD (H,A->C split)CMRF · HAC video+audio+flow, H,A->Ctop-1 accuracy (%): 55.61 -> 55.48No clear effect
add the third modality (flow) to MBCD vs best two-modalityMBCD · EPIC-Kitchenstop-1 accuracy (%): 63.08 -> 67.58Improved
add the third modality to ERMERM · EPIC-Kitchenstop-1 accuracy (%): 56.47 -> 50.55Hurt
replace CMRF with MBCD in-domainCMRF · EPIC-Kitchens in-domaintop-1 accuracy (%): 79.82 -> 81.60Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy