Journal
IEEE TRANSACTIONS ON MULTIMEDIA
Volume 22, Issue 11, Pages 2833-2843Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.2966863
Keywords
Face recognition; Face; Data mining; Measurement; Training; Sun; Image recognition; Face recognition; equalized margin (EqM) loss; intra-class scope; inter-class margin; deep learning
Categories
Funding
- Special Foundation for the Development of Strategic Emerging Industries of Shenzhennder [JCYJ20170817161845824]
Ask authors/readers for more resources
In this paper, we propose a new loss function, termed the equalized margin (EqM) loss, which is designed to make both intra-class scopes and inter-class margins similar over all classes, such that all the classes can be evenly distributed on the hypersphere of the feature space. The EqM loss controls both the lower limit of intra-class similarity by exploiting hard-sample mining and the upper limit of inter-class similarity by assuring equalized margins. Therefore, using the EqM loss, we can not only obtain more discriminative features, but also overcome the negative impacts from the data imbalance on the inter-class margins. We also observe that the EqM loss is stable with the variation of the scale in normalized Softmax. Furthermore, by conducting extensive experiments on LFW, YTF, CFP, MegaFace and IJB-B, we are able to verify the effectiveness and superiority of the EqM loss, compared with other state-of-the-art loss functions for face recognition.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available