Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
arXiv:2206.12772 · doi:10.1145/3503161.3548317
Abstract
We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically investigate the effects of data augmentations, and reveal that (1) composition of data augmentations plays a critical role, i.e. explicitly encouraging the audio-visual representations to be invariant to various transformations~({\em transformation invariance}); (2) enforcing geometric consistency substantially improves the quality of learned representations, i.e. the detected sound source should follow the same transformation applied on input video frames~({\em transformation equivariance}). Extensive experiments demonstrate that our model significantly outperforms previous methods on two sound localization benchmarks, namely, Flickr-SoundNet and VGG-Sound. Additionally, we also evaluate audio retrieval and cross-modal retrieval tasks. In both cases, our self-supervised models demonstrate superior retrieval performances, even competitive with the supervised approach in audio retrieval. This reveals the proposed framework learns strong multi-modal representations that are beneficial to sound localisation and generalization to further applications. \textit{All codes will be available}.
arXiv commentCamera-ready Version for ACMMM 2022, Project page is https://jinxiang-liu.github.io/SSL-TIE/
References in corpus (10)
- A Simple Framework for Contrastive Learning of Visual Representations
- Representation Learning with Contrastive Predictive Coding
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Bootstrap your own latent: A new approach to self-supervised Learning
- Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
- Audiovisual SlowFast Networks for Video Recognition
- Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
- Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
- Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes
- Class-aware Sounding Objects Localization via Audiovisual Correspondence