AI Paper Atlas

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

Contrastive Audio-Visual Masked Autoencoder

Yuan Gong, Andrew Rouditchenko, Alexander H. Liu, David Harwath, Leonid Karlinsky, Hilde Kuehne, James R. Glass

ICLR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 16 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 masked data modeling reconstruction loss to contrastive audio-visual learning (CAV-MAE vs CAV) (ablation)CAV-MAE · AudioSet-20KmAP (A-V): +2.0 mAP (38.5 to 40.5)Improved
add contrastive loss to masked autoencoder (CAV-MAE vs AV-MAE) (ablation)CAV-MAE · AudioSet-20KmAP (A-V): +3.1 mAP (37.4 to 40.5)Improved
add contrastive loss to masked autoencoder (CAV-MAE vs AV-MAE) (ablation)CAV-MAE · Visual→Audio retrieval on VGGSoundR@1: 0.1 to 14.7 R@1Improved
add modality-specific encoders before joint encoder (AV-MAE vs Vanilla AV-MAE) (ablation)AV-MAE · AudioSet-20KmAP (A-V): 37.4 vs 36.5 (A-V); 33.4 vs 32.7 (A)Improved
multi-modal CAV-MAE pretraining used for single-modal fine-tuning (vs Audio-MAE)CAV-MAE · AudioSet-20K audio-onlymAP: 34.2 to 37.7Improved
scale up batch size and pretraining epochs (CAV-MAE Scale+) (ablation)CAV-MAE · AudioSet-20KmAP (A-V): 40.5 to 42.0Improved
increase contrastive loss weight lambda_c from 0.01 to 0.1 or decrease to 0.001 (ablation)CAV-MAE · AudioSet-20KmAP (A-V): 39.3 (0.1) and 38.6 (0.001) vs 40.5Hurt
pretrain on AudioSet-2M then VGGSound vs VGGSound-only or AS-2M only (ablation)CAV-MAE · VGGSoundAccuracy: 65.9 vs 65.5 (AS-2M) and 64.2 (VS)Improved
normalize prediction target (ablation)CAV-MAE · AudioSet-20KmAP (A-V): 40.5 vs 40.5No clear effect
use multi-modal stream output for fine-tuning vs single-modal streams (ablation)CAV-MAE · AudioSet-20KmAP (A-V): 42.0 MM vs 41.3 SMImproved
use frame aggregation (averaging predictions over 10 frames) vs middle frame at inference (ablation)CAV-MAE · AudioSet-20KmAP (A-V): 40.9 to 42.0Improved
use time-frequency masking at 50% ratio instead of uniform 75% (ablation)CAV-MAE · VGGSoundAccuracy: 65.6 vs 65.4Improved

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