Back to Search
Start Over
Self-Supervised Audio-Visual Co-Segmentation
- Publication Year :
- 2019
-
Abstract
- Segmenting objects in images and separating sound sources in audio are challenging tasks, in part because traditional approaches require large amounts of labeled data. In this paper we develop a neural network model for visual object segmentation and sound source separation that learns from natural videos through self-supervision. The model is an extension of recently proposed work that maps image pixels to sounds. Here, we introduce a learning approach to disentangle concepts in the neural networks, and assign semantic categories to network feature channels to enable independent image segmentation and sound source separation after audio-visual training on videos. Our evaluations show that the disentangled model outperforms several baselines in semantic segmentation and sound source separation.<br />Comment: Accepted to ICASSP 2019
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.1904.09013
- Document Type :
- Working Paper