analiza aiqbench
This research addresses a practical limitation in few-shot audio classification by proposing a method that handles both increasing and decreasing class counts, rather than assuming only growth. By utilizing prototype adaptation and pseudo class-variable training, the approach dynamically adjusts its classifier structure to maintain accuracy across shifting taxonomies. The results demonstrate superior performance on standard benchmarks, offering a robust solution for real-world scenarios where label sets are fluid.
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
arXiv:2606.08898v1 Announce Type: cross Abstract: 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.
Abstract: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: this https URL.
This paper has been accepted for publication in Interspeech 2026. 4 Tables and 4 Figures
Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2606.08898 [eess.AS]
(or arXiv:2606.08898v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2606.08898 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 256 cuvinte