An Adaptive Plug-and-Play Network for Few-Shot Learning

TL;DR

This paper introduces an adaptive plug-and-play network for few-shot learning that enhances classification accuracy by reducing overfitting through a model-adaptive resizer and a fused similarity metric, achieving state-of-the-art results.

Contribution

It proposes a novel plug-and-play framework with a model-adaptive resizer and an adaptive similarity metric, improving few-shot learning performance without additional losses.

Findings

Boosts existing methods on standard datasets

Achieves state-of-the-art results on mini-ImageNet and tiered-ImageNet

Effectively alleviates overfitting in few-shot learning

Abstract

Few-shot learning (FSL) requires a model to classify new samples after learning from only a few samples. While remarkable results are achieved in existing methods, the performance of embedding and metrics determines the upper limit of classification accuracy in FSL. The bottleneck is that deep networks and complex metrics tend to induce overfitting in FSL, making it difficult to further improve the performance. Towards this, we propose plug-and-play model-adaptive resizer (MAR) and adaptive similarity metric (ASM) without any other losses. MAR retains high-resolution details to alleviate the overfitting problem caused by data scarcity, and ASM decouples the relationship between different metrics and then fuses them into an advanced one. Extensive experiments show that the proposed method could boost existing methods on two standard dataset and a fine-grained datasets, and achieve state-of-the-art results on mini-ImageNet and tiered-ImageNet.