Learning Discriminative Features with Class Encoder
This addresses the need for better supervised training methods in computer vision, particularly for face recognition, but it is incremental as it builds on existing auto-encoder and softmax techniques.
The paper tackles the problem of improving discriminative feature learning in deep neural networks by proposing a class-encoder that reconstructs samples within the same class to reduce intra-class variations, resulting in performance gains on classification and face recognition benchmarks.
Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the application of auto-encoders is usually limited to small, well aligned images. In this paper, we incorporate the supervised information to propose a novel formulation, namely class-encoder, whose training objective is to reconstruct a sample from another one of which the labels are identical. Class-encoder aims to minimize the intra-class variations in the feature space, and to learn a good discriminative manifolds on a class scale. We impose the class-encoder as a constraint into the softmax for better supervised training, and extend the reconstruction on feature-level to tackle the parameter size issue and translation issue. The experiments show that the class-encoder helps to improve the performance on benchmarks of classification and face recognition. This could also be a promising direction for fast training of face recognition models.