# Sample-Conditioned Representation Selection for Audio Few-Shot Learning

arXiv: https://arxiv.org/abs/2609.17076 · HTML: https://mlsanity.com/paper/2609.17076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement](https://mlsanity.com/paper/1903.06059/) (2019)
- [Finding Task-Relevant Features for Few-Shot Learning by Category Traversal](https://mlsanity.com/paper/1905.11116/) (2019)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [MetaAudio: A Few-Shot Audio Classification Benchmark](https://mlsanity.com/paper/2204.02121/) (2022)
- [Task Discrepancy Maximization for Fine-grained Few-Shot Classification](https://mlsanity.com/paper/2207.01376/) (2022)
- [Prototypical Contrastive Learning For Improved Few-Shot Audio Classification](https://mlsanity.com/paper/2509.10074/) (2025)
- [SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification](https://mlsanity.com/paper/2605.13672/) (2026)
- [From Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural Generation](https://mlsanity.com/paper/2606.14791/) (2026)

## Abstract (arXiv)

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/