Neural Class-Specific Regression for face verification
This work addresses scalability issues in face verification for biometrics and security applications, but it is incremental as it builds on prior kernel-based methods.
The authors tackled the challenge of applying class-specific subspace learning to large-scale face verification by reformulating it as a regression problem, enabling efficient linear, kernel, and neural network methods that were tested on medium- and large-scale datasets.
Face verification is a problem approached in the literature mainly using nonlinear class-specific subspace learning techniques. While it has been shown that kernel-based Class-Specific Discriminant Analysis is able to provide excellent performance in small- and medium-scale face verification problems, its application in today's large-scale problems is difficult due to its training space and computational requirements. In this paper, generalizing our previous work on kernel-based class-specific discriminant analysis, we show that class-specific subspace learning can be cast as a regression problem. This allows us to derive linear, (reduced) kernel and neural network-based class-specific discriminant analysis methods using efficient batch and/or iterative training schemes, suited for large-scale learning problems. We test the performance of these methods in two datasets describing medium- and large-scale face verification problems.