MAViL: Masked Audio-Video Learners
This work addresses the challenge of self-supervised learning in multimodal AI, offering a novel approach that outperforms externally supervised models on key benchmarks.
The paper tackles the problem of learning audio-visual representations by introducing MAViL, which combines masked reconstruction, contrastive learning, and self-training, achieving state-of-the-art results on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy).
We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks.