AI Paper Atlas

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

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

Hao Dong, Ismail Nejjar, Han Sun, Eleni Chatzi, Olga Fink

NeurIPS 2023 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 8 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
Use SimMMDG with video, audio, and optical flow instead of the strongest listed baselineMulti-source DG · EPIC-KitchensTop-1 accuracy: 56.59 -> 67.19Improved
Use SimMMDG with video, audio, and optical flow instead of the strongest listed baselineMulti-source DG · HACTop-1 accuracy: 66.74 -> 71.10Improved
Replace zero-filled missing audio features with cross-modal translated featuresSimMMDG · EPIC-Kitchens, video available and audio missingTop-1 accuracy: 59.24 -> 60.65Improved
Replace zero-filled missing video features with cross-modal translated featuresSimMMDG · EPIC-Kitchens, audio available and video missingTop-1 accuracy: 37.41 -> 45.38Improved
Add supervised contrastive learning (ablation)SimMMDG · EPIC-Kitchens multi-source DGTop-1 accuracy: 55.45 -> 58.67Improved
Add feature splitting without constraints (ablation)SimMMDG with supervised contrastive learning · EPIC-Kitchens multi-source DGTop-1 accuracy: 58.67 -> 57.77Hurt
Add distance loss to promote diversity between modality-specific and modality-shared features (ablation)SimMMDG with supervised contrastive learning and feature splitting · EPIC-Kitchens multi-source DGTop-1 accuracy: 57.77 -> 61.18Improved
Add cross-modal translation (ablation)SimMMDG with supervised contrastive learning, feature splitting, and distance loss · EPIC-Kitchens multi-source DGTop-1 accuracy: 61.18 -> 63.24Improved
Add supervised contrastive learning (ablation)SimMMDG with feature splitting, distance loss, and cross-modal translation · EPIC-Kitchens multi-source DGTop-1 accuracy: 60.25 -> 63.24Improved
Use ℓ2 distance rather than cosine similarity in the distance loss (ablation)SimMMDG · EPIC-Kitchens multi-source DGTop-1 accuracy: 58.00 -> 63.24Improved
Use ℓ2 distance rather than ℓ1 norm in the distance loss (ablation)SimMMDG · EPIC-Kitchens multi-source DGTop-1 accuracy: 58.95 -> 63.24Improved
Add Gradient BlendingSimMMDG · EPIC-Kitchens multi-source DGTop-1 accuracy: 63.24 -> 64.78Improved

Later papers that compared with this method

3 later accepted papers report SimMMDG as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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