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.
@article{arxiv.2210.07839,
title = {Contrastive Audio-Visual Masked Autoencoder},
author = {Yuan Gong and Andrew Rouditchenko and Alexander H. Liu and David Harwath and Leonid Karlinsky and Hilde Kuehne and James Glass},
journal= {arXiv preprint arXiv:2210.07839},
year = {2023}
}
Comments
Accepted at ICLR 2023 as a notable top 25% paper. Code and pretrained models are at https://github.com/yuangongnd/cav-mae