Work

Deep fisher faces

Year: 2017
Type: conference-paper
Abstract: Most current state-of-the-art methods for unconstrained face recognition use deep convolutional neural networks.Recently, it has been proposed to augment the typically used softmax cross-entropy loss by adding a center loss trying to minimize the distance between the face images and their class centers.In this work we further extend the center (intra-class) loss with an inter-class loss reminiscent of the popular early face recognition approach Fisherfaces.To this end we add a term that directly optimizes the distances of the class centers appearing in a batch in dependence of the input images.We evaluate the new loss on two popular databases for unconstrained face recognition, the Labeled Faces in the Wild and the Youtube Faces database.In both cases the new loss achieves competitive results.
Language: English
Open Access status: green
OpenAlex ID: W2893968952
FWCI: 0.231
Cites: 19
Cited by: 10
Related to: 10