A frozen residual-CNN embedding trained with pseudo-incremental augmentation plus a continually updated stochastic classifier improves few-shot class-incremental audio accuracy with lower complexity than most baselines.
Statistical comparisons of classifiers over mu ltiple data sets,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A prototype-based classifier with attention-fused embeddings from support and query samples enables few-shot open-set audio classification and outperforms prior methods on three public datasets.
citing papers explorer
-
Few-Shot Class-Incremental Audio Classification Using Pseudo-Incrementally Trained Embedding Learner and Continually Updated Stochastic Classifier
A frozen residual-CNN embedding trained with pseudo-incremental augmentation plus a continually updated stochastic classifier improves few-shot class-incremental audio accuracy with lower complexity than most baselines.
-
Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes
A prototype-based classifier with attention-fused embeddings from support and query samples enables few-shot open-set audio classification and outperforms prior methods on three public datasets.