Semi Supervised Learning for Few-Shot Audio Classification by Episodic Triplet Mining

Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. The performance of prototypical networks in extreme few-shot scenarios (like one-shot) degrades drastically, mainly due to the desuetude of variations within the clusters while constructing prototypes.

Data and Resources

Cite this as

Swapnil Bhosale, Rupayan Chakraborty, Sunil Kumar Kopparapu (2024). Dataset: Semi Supervised Learning for Few-Shot Audio Classification by Episodic Triplet Mining. https://doi.org/10.57702/x3qdppru

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2102.08074
Author Swapnil Bhosale
More Authors
Rupayan Chakraborty
Sunil Kumar Kopparapu