mlsanityData to 13 Oct 2026

Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training

arXiv 2606.08898 ↗First posted 8 Jun 2026eess.AS cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In the task of few-shot class-incremental audio classification, the number of classes is assumed to always increase without considering the possibility of decrease. However, the number of classes generally increases or decreases in practice. In this paper, we investigate a problem of Few-shot Class-variable Incremental Audio Classification (FCIAC), in which the number of classes increases or decreases. We propose a FCIAC method using prototype adaptation and pseudo class-variable training. The model in our method consists of an encoder and a classifier. The classifier is initialized by a class-variable prototype adaptation network, whose structure dynamically changes with the change of classes. In addition, we design a pseudo class-variable training strategy to enhance the model's adaptability to changing classes. Experiments on three public datasets show that our method exceeds previous methods in average accuracy. The code is at: https://github.com/cgq2971-afk/FCIAC.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

16 of 37 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  4. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  5. 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 175
  6. 2019BUT System Description to VoxCeleb Speaker Recognition Challenge 2019cited by 51
  7. 2023Multiscale Audio Spectrogram Transformer for Efficient Audio Classificationcited by 16
  8. 2023Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypescited by 10
  9. 2019Sound event detection via dilated convolutional recurrent neural networkscited by 8
  10. 2023Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypescited by 6
  11. 2021Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument soundscited by 5
  12. 2023Few-shot Class-incremental Audio Classification Using Stochastic Classifiercited by 4
4 more
  1. 2021Domestic activities clustering from audio recordings using convolutional capsule autoencoder networkcited by 3
  2. 2023HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classificationcited by 2
  3. 2023Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNetcited by 1
  4. 2025Fully Few-shot Class-incremental Audio Classification Using Multi-level Embedding Extractor and Ridge Regression Classifiercited by 1

Built on by

Not cited yet.