aiqbench analysis
This research introduces SAMPLESELECT, a novel method for few-shot audio classification that dynamically selects informative features while keeping the base encoder frozen to mitigate representation shifts. By leveraging differentiable Gumbel Top-k selection and contrastive losses, the approach achieves superior out-of-distribution accuracy compared to existing techniques. The work advances machine learning efficiency in low-data regimes by isolating class-dependent signal components without retraining core model weights.
Sample-Conditioned Representation Selection for Audio Few-Shot Learning
arXiv:2609.17076v1 Announce Type: new 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/
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 this https URL
Artificial Intelligence (cs.AI); Sound (cs.SD)
arXiv:2609.17076 [cs.AI]
(or arXiv:2609.17076v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.17076 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.
Full text under the publisher's open licence · 227 words
Related coverage
Self-Modeling Interventions Modulate Emergent Misalignment
LessWrong · Oct 5, 2026
Neural operator discovery from heterogeneous trajectories
arXiv · Jul 28, 2026
Diverse reasoning traces teach LLMs to make better decisions
Amazon Science · May 26, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026