# Stochastic-based Patch Filtering for Few-Shot Learning

arXiv: https://arxiv.org/abs/2508.10066 · HTML: https://mlsanity.com/paper/2508.10066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [Image Deformation Meta-Networks for One-Shot Learning](https://mlsanity.com/paper/1905.11641/) (2019)
- [Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation](https://mlsanity.com/paper/2210.04524/) (2022)
- [LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections](https://mlsanity.com/paper/2305.18287/) (2023)
- [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://mlsanity.com/paper/2103.13582/) (2021)
- [Rethinking Generalization in Few-Shot Classification](https://mlsanity.com/paper/2206.07267/) (2022)
- [Label Propagation for Zero-shot Classification with Vision-Language Models](https://mlsanity.com/paper/2404.04072/) (2024)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks](https://mlsanity.com/paper/2301.06957/) (2023)
- [Distributional Modeling on a Diet: One-shot Word Learning from Text Only](https://mlsanity.com/paper/1704.04550/) (2017)
- [Clustered-patch Element Connection for Few-shot Learning](https://mlsanity.com/paper/2304.10093/) (2023)
- [An Adaptive Plug-and-Play Network for Few-Shot Learning](https://mlsanity.com/paper/2302.09326/) (2023)
- [Class-relevant Patch Embedding Selection for Few-Shot Image Classification](https://mlsanity.com/paper/2405.03722/) (2024)

## Abstract (arXiv)

Food images present unique challenges for few-shot learning models due to their visual complexity and variability. For instance, a pasta dish might appear with various garnishes on different plates and in diverse lighting conditions and camera perspectives. This problem leads to losing focus on the most important elements when comparing the query with support images, resulting in misclassification. To address this issue, we propose Stochastic-based Patch Filtering for Few-Shot Learning (SPFF) to attend to the patch embeddings that show greater correlation with the class representation. The key concept of SPFF involves the stochastic filtering of patch embeddings, where patches less similar to the class-aware embedding are more likely to be discarded. With patch embedding filtered according to the probability of appearance, we use a similarity matrix that quantifies the relationship between the query image and its respective support images. Through a qualitative analysis, we demonstrate that SPFF effectively focuses on patches where class-specific food features are most prominent while successfully filtering out non-relevant patches. We validate our approach through extensive experiments on few-shot classification benchmarks: Food-101, VireoFood-172 and UECFood-256, outperforming the existing SoA methods.