Representative Local Feature Mining for Few-Shot Learning
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1730-1734
Abstract
Few-shot learning aims to recognize unseen images of new classes with only a few training examples. While great progress has been made with deep learning technology, most metric-based works rely on the measurement based on global feature representation of images, which is sensitive to background factors due to the scarcity of training data. Given this, we propose a novel method that chooses representative local features to facilitate few-shot learning. Specifically, we propose a "task-specific guided" strategy to mine local features that are task-specific and discriminative. For each task, we first mine representative local features for labeled images by a loss guided mechanism. Then these local features are used to guide a classifier to mine representative local features for unlabeled images. In this way, task-specific representative local features can be selected for better classification. We empirically show our method can effectively alleviate the negative effect introduced by background factors. Extensive experiments on two few-shot benchmarks show the effectiveness of the proposed method.Keywords
Funding Information
- Capital Health
- Peking University
This publication has 11 references indexed in Scilit:
- Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions2020
- Collect and Select: Semantic Alignment Metric Learning for Few-Shot Learning2019
- A Dual Attention Network with Semantic Embedding for Few-Shot LearningProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning2019
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal2019
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- ImageNet: A large-scale hierarchical image database2009