Class-relevant Patch Embedding Selection for Few-Shot Image Classification

원문 초록

Effective image classification hinges on discerning relevant features from both foreground and background ele- ments, with the foreground typically holding the critical informa- tion. While humans adeptly classify images with limited exposure, artificial neural networks often struggle with feature selection from rare samples. To address this challenge, we propose a novel method for selecting class-relevant patch embeddings. Our ap- proach involves splitting support and query images into patches, encoding them using a pre-trained Vision Transformer (ViT) to obtain class embeddings and patch embeddings, respectively. Subsequently, we filter patch embeddings using class embeddings to retain only the class-relevant ones. For each image, we calculate the similarity between class embedding and each patch embed- ding, sort the similarity sequence in descending order, and only retain top-ranked patch embeddings. By prioritizing similarity between the class embedding and patch embeddings, we select top-ranked patch embeddings to be fused with class embedding to form a comprehensive image representation, enhancing pattern recognition across instances. Our strategy effectively mitigates the impact of class-irrelevant patch embeddings, yielding improved performance in pre-trained models. Extensive experiments on popular few-shot classification benchmarks demonstrate the sim- plicity, efficacy, and computational efficiency of our approach, outperforming state-of-the-art baselines under both 5-shot and 1-shot scenarios.