A single ViT with two specialized class tokens, one per self-supervised pretext task, learns both timbre-focused and harmony-focused music representations and outperforms a much larger MLM model on most MIR benchmarks.
Towards proper contrastive self- supervised learning strategies for music audio representation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval
A single ViT with two specialized class tokens, one per self-supervised pretext task, learns both timbre-focused and harmony-focused music representations and outperforms a much larger MLM model on most MIR benchmarks.