Stochastic-based Patch Filtering for Few-Shot Learning
This addresses the problem of misclassification in few-shot learning for food images, which is incremental as it builds on existing methods with a novel filtering approach.
The paper tackled the problem of few-shot learning for food images, which are challenging due to visual complexity and variability, by proposing Stochastic-based Patch Filtering (SPFF) to focus on relevant patches, and it outperformed state-of-the-art methods on benchmarks like Food-101, VireoFood-172, and UECFood-256.
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.