MARANet: Multi-scale Adaptive Region Attention Network for Few-Shot Learning

Few-shot learning, which aims to classify unknown categories with fewer label samples, has become a research hotspot in computer vision because of its wide application. Objects will present different regional locations in nature, and the existing few-shot learning only focuses on the overall location information, while ignoring the impact of local key information on classification tasks. To solve this problem, (1) we propose a new multi-scale adaptive region attention network (MARANet), which makes use of the semantic similarity between images to make the model pay more attention to the areas that are beneficial to the classification task. (2) MARANet mainly includes two modules—the multi-scale feature generation module uses low-level features (LF) of different scales to solve the problem of different target scales in nature; the adaptive region metric module selects the LF of key regions by assigning masks to each classification task. We have conducted experiments on three common data sets (i.e. miniImageNet, CUB-200, and Stanford Cars). The experimental results show that the new category classification task of MARANet is \(1.1\%\sim 4.9\%\) higher than the existing methods.