Improving Few-shot Learning with Weakly-supervised Object Localization

TL;DR

This paper introduces a novel weakly-supervised object localization framework that improves few-shot learning by focusing on class-relevant regions, leading to better class representations and improved performance on benchmark datasets.

Contribution

It proposes a new method to generate class representations by localizing class objects from few examples, enhancing few-shot learning accuracy.

Findings

Outperforms baseline models on miniImageNet and tieredImageNet

Effective localization improves class feature quality

Enhanced features lead to better few-shot classification results

Abstract

Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling in the backend of the feature extractor may not produce an embedding that correctly focuses on the class object. In this work, we propose a novel framework that generates class representations by extracting features from class-relevant regions of the images. Given only a few exemplary images with image-level labels, our framework first localizes the class objects by spatially decomposing the similarity between the images and their class prototypes. Then, enhanced class representations are achieved from the localization results. We also propose a loss function to enhance distinctions of the refined features. Our method outperforms the baseline few-shot model in miniImageNet and tieredImageNet benchmarks.