MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations

2023/05/29 by Calum Heggan, Heggan, Calum, Tim Hospedales +5
Biochemistry, Genetics and Molecular Biology · Computer Science · #Audio and Speech Processing (eess.AS) #Cancer-related molecular mechanisms research #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2305.17191

openalex publication_date 2023/05/29 · openalex created_date 2023/05/31 · openalex updated_date 2026/07/28

Abstract

Contrastive self-supervised learning has gained attention for its ability to create high-quality representations from large unlabelled data sets. A key reason that these powerful features enable data-efficient learning of downstream tasks is that they provide augmentation invariance, which is often a useful inductive bias. However, the amount and type of invariances preferred is not known apriori, and varies across different downstream tasks. We therefore propose a multi-task self-supervised framework (MT-SLVR) that learns both variant and invariant features in a parameter-efficient manner. Our multi-task representation provides a strong and flexible feature that benefits diverse downstream tasks. We evaluate our approach on few-shot classification tasks drawn from a variety of audio domains and demonstrate improved classification performance on all of them

Related

• Multimodal Self-Supervised Learning of General Audio Representations
• Amortised Invariance Learning for Contrastive Self-Supervision
• Self-supervised learning method using multiple sampling strategies for general-purpose audio representation
• Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations
• Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data