Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning

Large-scale datasets are the cornerstone of selfsupervised representation learning. Existing algorithms extract learning signals by making certain assumptions about the data, e.g., spatio-temporal continuity and multimodal correspondence. Unfortunately, finding a large amount of data that satisfies such assumptions is sometimes not straightforward. This restricts the community to rely on datasets that require laborious annotation and/or manual filtering processes. In this paper, we describe a subset optimization approach for automatic dataset curation. Focusing on the scenario of audio-visual representation learning, we pose the problem as finding a subset that maximizes the mutual information between audio and visual channels in videos. We demonstrate that our approach finds videos with high audio-visual correspondence and show that selfsupervised models trained on our data, despite being automatically constructed, achieve similar downstream performances to existing video datasets with similar scales. The most significant benefit of our approach is scalability. We release the largest video dataset for audio-visual research collected automatically using our approach.