AI Paper Atlas

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

Robustness in Multimodal Learning under Train-Test Modality Mismatch

Brandon McKinzie, Vaishaal Shankar, Joseph Yitan Cheng, Yinfei Yang, Jonathon Shlens, Alexander T Toshev

ICML 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

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 MASD (modality augmented self-distillation) to contrastive pretraining (ablation)Contrastive learning · AudioSetOverall robustness R: 20.8 -> 24.1 (vs fine-tune baseline)Improved
Add MASD to MAE pretraining (ablation)MAE · AudioSetOverall robustness R: 3.8 -> 15.1Improved
Add WiseFT weight interpolation on top of MASD (ablation)Contrastive + MASD · AudioSetOverall robustness R: 24.1 -> 24.8 (overall); mainly fixes Missing at TestMixed
Replace downstream fine-tuning on AS-20K with fine-tuning on 2M labeled examples (ablation)Contrastive · AudioSetOverall robustness R: 20.8 -> 21.8 (still below MASD 24.1)Improved
Use Kinetics data (instead of AudioSet) as self-distillation data for MASD (ablation)Contrastive MASD on Kinetics-400 · Kinetics-400Overall robustness R: 23.5 (distill-on-AS) -> 26.9 (distill-on-Kinetics)Improved
Add MASD to contrastive learningContrastive learning · ImageNet-CaptionsOverall robustness R: 66.7 -> 80.8Improved
Add text as an extra pretraining/training modalityContrastive + MASD+WiseFT · AudioSet 20KmAP: 44.2 (AV) -> 49.4 (AVT)Improved
Adding MASD to MAE on AudioSet (ablation)MAE · AudioSetPerformance P (overall): 28.9 -> 30.6 (Pbest)Improved
Adding MASD to contrastive on AudioSet reduces robustness drop on Transferability and Added at Test setups (ablation)Contrastive · AudioSetTransferability robustness: 13.0 -> 24.1Improved
Use MASD on MAE with Kinetics: distill-on-Kinetics vs fine-tuneMAE · Kinetics-400Overall robustness R: 17.1 -> 27.6Improved

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