EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning

TL;DR

EquiAV introduces an equivariance-based framework for audio-visual contrastive learning, enhancing robustness and performance by effectively leveraging data augmentations without disrupting input correspondence.

Contribution

The paper proposes a novel equivariance-based approach with a shared attention predictor, improving audio-visual contrastive learning efficiency and robustness over prior methods.

Findings

Outperforms previous methods on multiple benchmarks

Effective with minimal computational overhead

Validates through extensive ablation studies

Abstract

Recent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning methods, audio-visual learning has struggled to fully harness these benefits, as augmentations can easily disrupt the correspondence between input pairs. To address this limitation, we introduce EquiAV, a novel framework that leverages equivariance for audio-visual contrastive learning. Our approach begins with extending equivariance to audio-visual learning, facilitated by a shared attention-based transformation predictor. It enables the aggregation of features from diverse augmentations into a representative embedding, providing robust supervision. Notably, this is achieved with minimal computational overhead. Extensive ablation studies and qualitative results verify the effectiveness of our method. EquiAV outperforms previous works across various audio-visual benchmarks. The code is available on https://github.com/JongSuk1/EquiAV.