Paper Info
Title
Adaptive Hardness Indicator Softmax for Deep Face Recognition
Abstract
Due to their simplicity and efficiency, the margin-based Softmax losses are proposed to enhance feature discrimination in face recognition. Recently, the strategy of hard sample mining is incorporated to the margin-based Softmax losses for focusing the misclassified samples and achieves superior performance. However, the current mining-based Softmax losses indicate the sample difficultness only from the perspective of the negative cosine similarity, which is local and not robust. To obtain more discriminative deep face features, a novel adaptive hardness indicator Softmax (AHI-Softmax) loss is proposed in this paper to fully exploit the hardness information of samples. Our AHI-Softmax firstly defines a global sample hardness indicator function that integrates three difficultness factors to robustly indicate the level of "hardness" in numerical form. Then, a training stage indicator is incorporated to avoid the convergence issue. Finally, a novel sample-related modulation coefficient of the negative cosine similarity which combines the global and local hardness indicator will be defined to further enhance the differentiation of constraints imposed on samples. The experimental results on general face datasets, including LFW, AgeDB-30, CFP-FP, CALFW, CPLFW, MegaFace, IJB-B and IJB-C, show that our method can obtain more discriminative features and achieve superior verification and recognition results.
Year
DOI
Venue
2022
10.1142/S0218001422560092
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
Keywords
DocType
Volume
Deep face recognition, margin-based loss functions, hard samples, adaptive mining-based strategies
Journal
36
Issue
ISSN
Citations 
04
0218-0014
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Mao Cai100.34
Ning Cheng200.34
Chunzheng Cao301.01
Jianwei Yang45812.73
Yunjie Chen500.68