Skip to content

Sample-Conditioned Representation Selection for Audio Few-Shot Learning

Sep 2026 · arXiv.org · Vol abs/2609.17076 · 0 citations · 18 references
Computer Science

TL;DR

Across ResNet12 and Conv64 in 5-way 1-shot and 5-shot evaluation, SAMPLESELECT gives the best OOD accuracy among the compared methods and improves the matched full-representation control by 4.90-8.38 percentage points.

Abstract

Few-shot audio classifiers may rely on foreground-background co-occurrences and fail when those correlations shift. On SpurAudio, the resulting representation shift is concentrated and class dependent: for ResNet12, the top 10 percent of channels explain 82.80 percent of the null-corrected shift contribution. We propose SAMPLESELECT, which predicts a fixed-budget feature mask independently for each input while keeping the encoder and source classifier frozen. Training uses differentiable Gumbel Top-k selection with foreground classification and cross-background contrastive losses; inference uses deterministic Top-k masks and support-only linear adaptation. Across ResNet12 and Conv64 in 5-way 1-shot and 5-shot evaluation, SAMPLESELECT gives the best OOD accuracy among the compared methods and improves the matched full-representation control by 4.90-8.38 percentage points. Ablations and representation analyses further support the learned selection mechanism. Code is available at https://github.com/Cross-Innovation-Lab/SAMPLESELECT/

View source

Similar papers

Preprint Aug 2026

SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification

SPECTRA is a framework built on a frozen encoder which adds three components, a lightweight trainable adapter that calibrates the generic embeddings to the task, an exemplar-free anti-forgetting scheme, and a transductive optimal-transport refinement of prototypes at test time.

Giries Abu Ayoub, L. Mualem, Simon Korman · 0 citations
Open access Sep 2026

Self-supervised audio representation learning model based on time-frequency decoupling and masked reconstruction

A self-supervised model that integrates a time-frequency decoupled (TF-D) stem with masked latent reconstruction with the strongest overall transfer results among the internal variants and a competitive balance among representation quality, encoder scale, and inference efficiency is proposed.

Jie Xu, Yu-Hao Dai, Zhi-Feng Wang · 0 citations
Sep 2026

Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification

Spectral Transductive Refinement (STR), a training-free transductive inference rule that exploits the geometry of the complete support-query episode, operating entirely at inference time, attains the highest 1-shot average among compared methods and remains competitive at 5-shot, rivalling approaches relying on heavy s...

F. Rahman, S. Rohan, Mahmound Sayed et al. · 0 citations
Review Open access Sep 2026

FEW-SHOT IMAGE CLASSIFICATION: A SURVEY

Few-shot image classification (FSIC) addresses image recognition when only a few labeled examples are available for each novel class. This survey reviews five major FSIC method families: meta-learning, transfer learning, data augmentation, attribute-based methods, and vision-language model adaptation. The $N$-way $K$-s...

A. Daneshpour, Stefan Bucz, D. Jantassova et al. · 0 citations
Review Open access Sep 2026

Mathematical Optimization and Advanced Algorithms for Few-Shot and Zero-Shot Visual Learning: An Optimization-Centered Review

A unified comparison of attribute-based ZSL, episodic meta-learning, metric and prototype estimators, graph and optimal-transport inference, generative any-shot models, and adaptation of vision–language models is analyzed.

Jie Li, Yu-Bo Sun, Xun Du et al. · 0 citations
Conference Aug 2026

Robust Noisy-Label Learning: A Novel Class-Specific Autoencoder-Guided Sample Selection Framework

Deep learning has been extensively applied to sample selection. However, the performance of deep learning-based sample selection methods can be substantially degraded when training data are contaminated by noisy labels, a common issue in practical industrial settings. To address this challenge, this paper proposes Clas...

Hao-Bin Cao, Zi-Dong Wang, Wei-Bo Liu et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.