Sample-Conditioned Representation Selection for Audio Few-Shot Learning

• URL: http://arxiv.org/abs/2609.17076v1
• Date: Tue, 15 Sep 2026 12:15:12 GMT
• Title: Sample-Conditioned Representation Selection for Audio Few-Shot Learning
• Abstract summary: Few-shot audio classifiers may rely on foreground-background co-occurrences and fail when those correlations shift.<n>We propose SAMPLESELECT, which predicts a fixed-budget feature mask independently for each input.<n>It improves the matched full-representation control by 4.90-8.38 percentage points.
• Score: 14.872888820695666
• License: http://creativecommons.org/licenses/by/4.0/
• 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/

Related papers

• Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks [22.452076838251575]
  Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs.<n>We propose Distributional Feature Coverage Sample Selection (DFCS), a training-free, trigger-agnostic method that clusters fixed pretrained features into one region per poisoning slot.<n>Across BadNets and Blended attacks on CIFAR-10, Tiny-ImageNet, and Imagenette, DFCS achieves the highest mean attack success rate among seven selectors in all six dataset--attack settings.
  arXiv  Detail & Related papers  (2026-08-10T02:52:24Z)
• Stepwise Token Selection for Efficient Multimodal Large Language Models [0.7233065479782755]
  We introduce a pointer-style selection mechanism that iteratively chooses informative tokens, conditioning each decision on previously selected ones, and dynamically determines when to stop.<n>Under aggressive pruning that removes 88.9% of visual tokens, our method preserves 94.6% of the original accuracy while achieving a 1.88x speed-up in prefill latency.
  arXiv  Detail & Related papers  (2026-06-14T23:50:08Z)
• Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models [59.51249894128724]
  Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration.<n>We propose ADAS, a training-free reranking rule for parallel masked diffusion decoding.
  arXiv  Detail & Related papers  (2026-06-09T13:17:27Z)
• dVoting: Fast Voting for dLLMs [71.572316901001]
  Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling.<n>dLLMs can generate tokens at arbitrary positions in parallel, endowing them with significant potential for parallel test-time scaling.<n>We introduce dVoting, a fast voting technique that boosts reasoning capability without training, with only an acceptable extra computational overhead.
  arXiv  Detail & Related papers  (2026-02-12T16:35:05Z)
• MARS-Sep: Multimodal-Aligned Reinforced Sound Separation [72.85468563236005]
  MARS-Sep is a reinforcement learning framework for sound separation.<n>It learns a factorized Beta mask policy that is optimized by a clipped trust-region surrogate.<n>Experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation.
  arXiv  Detail & Related papers  (2025-10-12T09:05:28Z)
• Reproducible Machine Learning-based Voice Pathology Detection: Introducing the Pitch Difference Feature [1.7779568951268254]
  We introduce a novel methodology for voice pathology detection using the publicly available Saarbr"ucken Voice Database.<n>We evaluate six machine learning (ML) algorithms -- support vector machine, k-nearest neighbors, naive Bayes, decision tree, random forest, and AdaBoost.<n>Our approach 85.61%, 84.69% and 85.22% unweighted average recall (UAR) for females, males and combined results respectively.
  arXiv  Detail & Related papers  (2024-10-14T14:17:52Z)
• The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing [85.85160896547698]
  Real-life applications of deep neural networks are hindered by their unsteady predictions when faced with noisy inputs and adversarial attacks. We show how to design an efficient classifier with a certified radius by relying on noise injection into the inputs. Our novel certification procedure allows us to use pre-trained models with randomized smoothing, effectively improving the current certification radius in a zero-shot manner.
  arXiv  Detail & Related papers  (2023-09-28T22:41:47Z)
• Speech Corpora Divergence Based Unsupervised Data Selection for ASR [30.224456184969693]
  This study proposes a unsupervised target-aware data selection method based on speech corpora divergence (SCD) Experiments show that the proposed SCD data selection can realize 14.8% relative improvements to the random selection.
  arXiv  Detail & Related papers  (2023-02-26T03:26:26Z)
• Explaining Cross-Domain Recognition with Interpretable Deep Classifier [100.63114424262234]
  Interpretable Deep (IDC) learns the nearest source samples of a target sample as evidence upon which the classifier makes the decision. Our IDC leads to a more explainable model with almost no accuracy degradation and effectively calibrates classification for optimum reject options.
  arXiv  Detail & Related papers  (2022-11-15T15:58:56Z)
• UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning [89.56465237941013]
  We propose UNICON, a simple yet effective sample selection method which is robust to high label noise. We obtain an 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with a 90% noise rate.
  arXiv  Detail & Related papers  (2022-03-28T07:36:36Z)
• Decoding Imagined Speech using Wavelet Features and Deep Neural Networks [2.4063592468412267]
  This paper proposes a novel approach that uses deep neural networks for classifying imagined speech. The proposed approach employs only the EEG channels over specific areas of the brain for classification, and derives distinct feature vectors from each of those channels. The proposed architecture and the approach of treating the data have resulted in an average classification accuracy of 57.15%, which is an improvement of around 35% over the state-of-the-art results.
  arXiv  Detail & Related papers  (2020-03-19T00:36:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.