Face++ paper in ACM Multimedia 2014
Learning Compact Face Representation: Packing a Face into an int32
Haoqiang Fan, Mu Yang, Zhimin Cao, Yuning Jiang, Qi Yin [PDF]
This paper addresses the problem of producing very compact representation of a face image for large-scale face search and analysis tasks. In tradition, the compactness of face rep- resentation is achieved by a dimension reduction step after representation extraction. However, the dimension reduc- tion usually degrades the discriminative ability of the orig- inal representation drastically. In this paper, we present a deep learning framework which optimizes the compactness and discriminative ability jointly. The learnt representation can be as compact as 32 bit (same as the int32) and still produce highly discriminative performance (91.4% on LFW benchmark). Based on the extreme compactness, we show that traditional face analysis tasks (e.g. gender analysis) can be eﬀectively solved by a Look-Up-Table approach given a large-scale face data set.