HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classification
Not on the map. Why?
Abstract (arXiv)
Few-shot audio classification is an emerging topic that attracts more and more attention from the research community. Most existing work ignores the specificity of the form of the audio spectrogram and focuses largely on the embedding space borrowed from image tasks, while in this work, we aim to take advantage of this special audio format and propose a new method by hallucinating high-frequency and low-frequency parts as structured concepts. Extensive experiments on ESC-50 and our curated balanced Kaggle18 dataset show the proposed method outperforms the baseline by a notable margin. The way that our method hallucinates high-frequency and low-frequency parts also enables its interpretability and opens up new potentials for the few-shot audio classification.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 27 Feb 2023.
Builds on
17 of 26 references.
References · 17
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
- 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
- 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
- 2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
- 2017Knowledge Transfer from Weakly Labeled Audio using Convolutional Neural Network for Sound Events and Scenescited by 20
5 more
- 2018Learning to match transient sound events using attentional similarity for few-shot sound recognitioncited by 13
- 2020Few-shot acoustic event detection via meta-learningcited by 13
- 2018Training neural audio classifiers with few datacited by 8
- 2020A Study of Few-Shot Audio Classificationcited by 5
- 2022Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detectioncited by 5
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.