Face verification algorithm based on Angular Margin triplet

In recent years, the face recognition algorithm based on CNN mainly focuses on the improvement of loss function. This paper improves the softmax loss function from two aspects: one is to normalize the weight and features of the loss function, the other is to introduce in class cosine similarity judg...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 1820; číslo 1; s. 12189
Hlavní autoři: Wang, Ning, Meng, Tao, Chen, Xiaoyong, Yuan, Dunlei, Yue, Qihong, Liu, Xiangqian
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.03.2021
Témata:
Algorithms
Face recognition
Physics
Trigonometric functions
ISSN:1742-6588, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In recent years, the face recognition algorithm based on CNN mainly focuses on the improvement of loss function. This paper improves the softmax loss function from two aspects: one is to normalize the weight and features of the loss function, the other is to introduce in class cosine similarity judgment on the basis of the original loss function. These improvements eventually make the distribution of features within the class closer and the distance between classes as far as possible. The recognition accuracy and generalization ability of the network are enhanced.
Bibliografie:ObjectType-Conference Proceeding-1
SourceType-Scholarly Journals-1
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1820/1/012189