Multi-scale Adaptive Task Attention Network for Few-Shot Learning

30 Nov 2020  ·  Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen ·

The goal of few-shot learning is to classify unseen categories with few labeled samples. Recently, the low-level information metric-learning based methods have achieved satisfying performance, since local representations (LRs) are more consistent between seen and unseen classes. However, most of these methods deal with each category in the support set independently, which is not sufficient to measure the relation between features, especially in a certain task. Moreover, the low-level information-based metric learning method suffers when dominant objects of different scales exist in a complex background. To address these issues, this paper proposes a novel Multi-scale Adaptive Task Attention Network (MATANet) for few-shot learning. Specifically, we first use a multi-scale feature generator to generate multiple features at different scales. Then, an adaptive task attention module is proposed to select the most important LRs among the entire task. Afterwards, a similarity-to-class module and a fusion layer are utilized to calculate a joint multi-scale similarity between the query image and the support set. Extensive experiments on popular benchmarks clearly show the effectiveness of the proposed MATANet compared with state-of-the-art methods.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification CUB-200-2011 5-way (1-shot) MATANet Accuracy 67.33 # 1
Few-Shot Image Classification CUB-200-2011 5-way (5-shot) MATANet Accuracy 83.92 # 1
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MATANet Accuracy 53.63 # 67
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MATANet Accuracy 72.67 # 56
Few-Shot Image Classification Stanford Cars 5-way (1-shot) MATANet Accuracy 73.15 # 1
Few-Shot Image Classification Stanford Cars 5-way (5-shot) MATANet Accuracy 91.89 # 1
Few-Shot Image Classification Stanford Dogs 5-way (1-shot) MATANet Accuracy 55.63 # 2
Few-Shot Image Classification Stanford Dogs 5-way (5-shot) MATANet Accuracy 70.29 # 2

Methods


No methods listed for this paper. Add relevant methods here