Multi-scale Comparison Network for Few-Shot Learning

Few-shot learning, which learns from a small number of samples, is an emerging field in multimedia. Through systematically exploring influences of scale information, including multi-scale feature extraction, multi-scale comparison and increased parameters brought by multiple scales, in this paper, we present a novel end-to-end model called Multi-scale Comparison Network (MSCN) for few-shot learning. The proposed MSCN uses different scale convolutions for comparison to solve the problem of excessive gaps between target sizes in the images during fewshot learning. It first uses a 4-layer encoder to encode support and testing samples to obtain their feature maps. After deep splicing these feature maps, the proposed MSCN further uses a comparator comprising two layers of multi-scale comparative modules and two fully connected layers to derive the similarity between support and testing samples. Experimental results on two benchmark datasets including Omniglot and miniImagenet shows the effectiveness of the proposed MSCN, which has averagely 2% improvement on miniImagenet in all experimental results compared with the recent Relation Network.