Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes
Not on the map. Why?
Abstract (arXiv)
Most existing audio classification methods suppose that each query (testing) sample belongs to a class of support (training) samples, and misrecognize samples of unseen classes as seen classes (cannot reject samples of unseen classes). In this study, we propose a method for Few-shot Open-set Audio Classification (FOAC), which can recognize query samples of seen classes after updating the model using a few support samples, and meanwhile reject query samples from unseen classes. We design a model consisting of an encoder and a classifier. The encoder is the backbone of a ResNet used for extracting embeddings. The classifier consists of prototype generators of few-shot classes and open-set classes. Prototypes of few-shot classes are obtained by fusing the class-discriminative information of support and query embeddings and by assigning larger weighting coefficient to representative part of the support embeddings. One prototype is generated for open-set classes using the proposed prototype generator. The encoder is trained with abundant samples of base classes in supervised manner, and then the prototypes of base classes are generated under the supervision of a joint loss. The classifier is trained using a few samples of few-shot classes in a meta-training way. Three public datasets (LS-100, NSynth-100, and FSC-89) are used to assess the performance of our method. Experiments show that our method has advantage over prior methods in AUROC and accuracy. This advantage has statistical significance for most prior methods. Our method has lower computational complexity than most prior methods. The code is at https://github.com/Jessytan/FOAC-AIFP.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 67 references that are in the map. First posted on arXiv 1 Jul 2026.
Builds on
37 of 67 references.
References · 37
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2020Meta-Learning in Neural Networks: A Surveycited by 950
- 2018Recent Advances in Open Set Recognition: A Surveycited by 310
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
- 2016Learning to Optimizecited by 195
- 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 127
- 2023A Closer Look at Few-shot Classification Againcited by 46
- 2023Audio-Visual Class-Incremental Learningcited by 33
- 2020Task-Adaptive Negative Envision for Few-Shot Open-Set Recognitioncited by 14
25 more
- 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
- 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
- 2023Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypescited by 10
- 2023Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systemscited by 9
- 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
- 2024LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Taggingcited by 7
- 2020Sound Event Detection with Depthwise Separable and Dilated Convolutionscited by 6
- 2023Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypescited by 6
- 2023LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competitioncited by 6
- 2022MARS: Meta-Learning as Score Matching in the Function Spacecited by 5
- 2023Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorizationcited by 5
- 2023MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Taskscited by 4
- 2023Few-shot Class-incremental Audio Classification Using Stochastic Classifiercited by 4
- 2023Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iterationcited by 4
- 2020An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environmentscited by 3
- 2021Domestic activities clustering from audio recordings using convolutional capsule autoencoder networkcited by 3
- 2022openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformercited by 3
- 2024Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractorcited by 3
- 2024On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classificationcited by 2
- 2024UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detectioncited by 2
- 2024Episodic fine-tuning prototypical networks for optimization-based few-shot learning: Application to audio classificationcited by 2
- 2022Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Networkcited by 1
- 2023Speaker verification using attentive multi-scale convolutional recurrent networkcited by 1
- 2023Lightweight Speaker Verification Using Transformation Module with Feature Partition and Fusioncited by 1
- 2024Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Networkcited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.