Slot Attention-based Feature Filtering for Few-Shot Learning

TL;DR

This paper introduces SAFF, a novel method using slot attention to filter irrelevant features in few-shot learning, significantly improving classification accuracy by focusing on meaningful information.

Contribution

SAFF uniquely integrates slot attention with patch embeddings to effectively discriminate and filter weak features in few-shot learning scenarios.

Findings

Outperforms existing methods on CIFAR-FS, FC100, miniImageNet, and tieredImageNet.

Slot attention captures more discriminative features than other attention mechanisms.

Filtering irrelevant features enhances few-shot classification accuracy.

Abstract

Irrelevant features can significantly degrade few-shot learn ing performance. This problem is used to match queries and support images based on meaningful similarities despite the limited data. However, in this process, non-relevant fea tures such as background elements can easily lead to confu sion and misclassification. To address this issue, we pro pose Slot Attention-based Feature Filtering for Few-Shot Learning (SAFF) that leverages slot attention mechanisms to discriminate and filter weak features, thereby improving few-shot classification performance. The key innovation of SAFF lies in its integration of slot attention with patch em beddings, unifying class-aware slots into a single attention mechanism to filter irrelevant features effectively. We intro duce a similarity matrix that computes across support and query images to quantify the relevance of filtered embed dings for classification. Through experiments, we demon strate that Slot Attention performs better than other atten tion mechanisms, capturing discriminative features while reducing irrelevant information. We validate our approach through extensive experiments on few-shot learning bench marks: CIFAR-FS, FC100, miniImageNet and tieredIma geNet, outperforming several state-of-the-art methods.