Low-Shot Face Recognition With Hybrid Classifiers

Yue Wu, Hongfu Liu, Yun Fu; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1933-1939

In this paper, we present our solution to the MS-Celeb-1M Low-shot Face Recognition Challenge. This challenge aims to recognize 21,000 celebrities, in which 20,000 celebrities (Base Set) come with 50-100 images per person. But only one training image is provided for each person in the rest 1,000 celebrities (Novel Set). Given the dispersion in the number of training samples between Base Set and Novel Set, it is hard to build a single classifier that works well for both sets. To solve this problem, a framework with hybrid classifiers is proposed to ensemble different inferences from multiple classifiers. This decomposes a single classifier for all data into multiple classifiers that each works well for a part of data. Extensive experiments on MS-Celeb-1M Low-shot dataset demonstrate the superiority of the proposed method. Our solution wins the challenge in the track of without external data.