MS-Celeb-1M: {A} Dataset and Benchmark for Large-Scale Face Recognition
Yandong Guo and Lei Zhang and Yuxiao Hu and Xiaodong He and Jianfeng Gao

@article{dblp:journals/corr/guozhhg16,
author= {Yandong Guo and               Lei Zhang and               Yuxiao Hu and               Xiaodong He and               Jianfeng Gao},
title= {MS-Celeb-1M: {A} Dataset and Benchmark for Large-Scale Face Recognition},
journal= {CoRR},
volume= {abs/1607.08221},
year= {2016},
url= {http://arxiv.org/abs/1607.08221},
archiveprefix= {arXiv},
eprint= {1607.08221},
timestamp= {Mon, 13 Aug 2018 16:46:27 +0200},
biburl= {https://dblp.org/rec/bib/journals/corr/GuoZHHG16},
bibsource= {dblp computer science bibliography, https://dblp.org},
abstract= {In this paper, we design a benchmark task and provide the associated datasets for recognizing face images and link them to corresponding entity keys in a knowledge base. More specifically, we propose a benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data. The rich information provided by the knowledge base helps to conduct disambiguation and improve the recognition accuracy, and contributes to various real-world applications, such as image captioning and news video analysis. Associated with this task, we design and provide concrete measurement set, evaluation protocol, as well as training data. We also present in details our experiment setup and report promising baseline results. Our benchmark task could lead to one of the largest classification problems in computer vision. To the best of our knowledge, our training dataset, which contains 10M images in version 1, is the largest publicly available one in the world.
},
keywords= {},
terms= {},
license= {},
superseded= {}
}