Multi-Scale Adaptive Task Attention Network for Few-Shot Learning
Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen
Abstract
Few-shot learning has aroused considerable interest in recent years, which aims to recognize unseen categories by using a few labeled samples. In various few-shot methods, pixel-level metric-learning based methods have achieved promising performance. However, most of these methods deal with each category in the support set independently, which may be insufficient to measure the relations among features, especially in a specific task. Besides, the coexistence of dominant objects at different scales may degrade the performance of these methods. To address these issues, a novel Multi-Scale Adaptive Task Attention Network, MATANet for short, is proposed for few-shot learning. In MATANet, a multi-scale feature generator is first constructed to extract the image features at different scales. Then, an adaptive task attention module is built to select the most important local representations among the entire task. Finally, a similarity-to-class module is adapted to measure the similarities between query and support set. Extensive experiments on popular benchmarks show the effectiveness of the proposed MATANet compared with state-of-the-art methods. Our source code is available at: https://github.com/chenhaoxing/MATANet.