EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers

TL;DR

EfficientFSL introduces a lightweight, query-only fine-tuning framework for Vision Transformers that achieves high few-shot classification accuracy with minimal computational resources by leveraging task-specific query synthesis and multi-layer feature fusion.

Contribution

The paper proposes a novel query-only fine-tuning method for ViTs that reduces training overhead while maintaining competitive performance in few-shot classification tasks.

Findings

Achieves state-of-the-art results on multiple few-shot datasets.

Reduces computational cost significantly compared to full fine-tuning.

Demonstrates robustness across in-domain and cross-domain scenarios.

Abstract

Large models such as Vision Transformers (ViTs) have demonstrated remarkable superiority over smaller architectures like ResNet in few-shot classification, owing to their powerful representational capacity. However, fine-tuning such large models demands extensive GPU memory and prolonged training time, making them impractical for many real-world low-resource scenarios. To bridge this gap, we propose EfficientFSL, a query-only fine-tuning framework tailored specifically for few-shot classification with ViT, which achieves competitive performance while significantly reducing computational overhead. EfficientFSL fully leverages the knowledge embedded in the pre-trained model and its strong comprehension ability, achieving high classification accuracy with an extremely small number of tunable parameters. Specifically, we introduce a lightweight trainable Forward Block to synthesize task-specific queries that extract informative features from the intermediate representations of the pre-trained model in a query-only manner. We further propose a Combine Block to fuse multi-layer outputs, enhancing the depth and robustness of feature representations. Finally, a Support-Query Attention Block mitigates distribution shift by adjusting prototypes to align with the query set distribution. With minimal trainable parameters, EfficientFSL achieves state-of-the-art performance on four in-domain few-shot datasets and six cross-domain datasets, demonstrating its effectiveness in real-world applications.