Virtual presentation / top 25% paper
Contrastive Audio-Visual Masked Autoencoder
Yuan Gong · Andrew Rouditchenko · Alexander Liu · David Harwath · Leonid Karlinsky · Hilde Kuehne · James R Glass
Keywords: [ Applications ] [ masked autoencoder ] [ Multi-Modal Learning ] [ audio-visual learning ] [ self-supervised learning ] [ contrastive learning ]
In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by combining contrastive learning and masked data modeling, two major self-supervised learning frameworks, to learn a joint and coordinated audio-visual representation.Our experiments show that the contrastive audio-visual correspondence learning objective not only enables the model to perform audio-visual retrieval tasks, but also helps the model learn a better joint representation. As a result, our fully self-supervised pretrained CAV-MAE achieves a new SOTA accuracy of 65.9% on VGGSound, and is comparable with the previous best supervised pretrained model on AudioSet in the audio-visual event classification task. Code and pretrained models are at https://github.com/yuangongnd/cav-mae.