Unsupervised Few-Shot Audio Classification
1 papers with code • 0 benchmarks • 0 datasets
In few-shot unsupervised classification, we assume that at the model pre-training stage, only unlabelled data is available. This contrasts the typical case where we assume labelled data is available for pre-training.
Benchmarks
These leaderboards are used to track progress in Unsupervised Few-Shot Audio Classification
No evaluation results yet. Help compare methods by
submitting
evaluation metrics.
Most implemented papers
MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations
Contrastive self-supervised learning has gained attention for its ability to create high-quality representations from large unlabelled data sets.