Slot Attention-based Feature Filtering for Few-Shot Learning
This work addresses a specific bottleneck in few-shot learning for computer vision by filtering irrelevant features to enhance classification accuracy, representing an incremental improvement over existing attention-based methods.
The paper tackles the problem of irrelevant features degrading few-shot learning performance by proposing Slot Attention-based Feature Filtering (SAFF), which integrates slot attention with patch embeddings to filter out non-relevant features like background elements, resulting in improved classification performance that outperforms state-of-the-art methods on benchmarks such as CIFAR-FS, FC100, miniImageNet, and tieredImageNet.
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.