Sequential Contrastive Audio-Visual Learning

TL;DR

This paper introduces Sequential Contrastive Audio-Visual Learning (SCAV), a novel approach that leverages the sequential nature of audio-visual data for improved retrieval performance, outperforming traditional aggregation-based methods.

Contribution

The paper proposes SCAV, a contrastive learning method that uses non-aggregated sequential representations, enhancing fine-grained information capture and retrieval accuracy.

Findings

SCAV achieves up to 3.5x better recall than traditional methods.

Models trained with SCAV are flexible with different retrieval metrics.

SCAV demonstrates effectiveness on VGGSound and Music datasets.

Abstract

Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video datasets. However, conventional contrastive audio-visual learning (CAV) methodologies often rely on aggregated representations derived through temporal aggregation, neglecting the intrinsic sequential nature of the data. This oversight raises concerns regarding the ability of standard approaches to capture and utilize fine-grained information within sequences. In response to this limitation, we propose sequential contrastive audiovisual learning (SCAV), which contrasts examples based on their non-aggregated representation space using multidimensional sequential distances. Audio-visual retrieval experiments with the VGGSound and Music datasets demonstrate the effectiveness of SCAV, with up to 3.5x relative improvements in recall against traditional aggregation-based contrastive learning and other previously proposed methods, which utilize more parameters and data. We also show that models trained with SCAV exhibit a significant degree of flexibility regarding the metric employed for retrieval, allowing us to use a hybrid retrieval approach that is both effective and efficient.