Harnessing Geometric Constraints from Emotion Labels to improve Face Verification

Autor:	Ramakrishnan, Anand, Pham, Minh, Whitehill, Jacob
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Computational Geometry Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	For the task of face verification, we explore the utility of harnessing auxiliary facial emotion labels to impose explicit geometric constraints on the embedding space when training deep embedding models. We introduce several novel loss functions that, in conjunction with a standard Triplet Loss [43], or ArcFace loss [10], provide geometric constraints on the embedding space; the labels for our loss functions can be provided using either manually annotated or automatically detected auxiliary emotion labels. Our method is implemented purely in terms of the loss function and does not require any changes to the neural network backbone of the embedding function. Comment: 8 pages, 3 figures, 2 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2103.03862 Zobrazit plný text záznamu View this record from Arxiv