DeepVisage: Making face recognition simple yet with powerful generalization skills

TL;DR

DeepVisage introduces a simple yet powerful CNN-based face recognition method that emphasizes ease of training and strong generalization, achieving state-of-the-art results without complex loss functions or multiple models.

Contribution

The paper proposes a residual learning CNN model for face recognition that is easy to train and generalizes well across datasets, avoiding complex training strategies.

Findings

Achieves state-of-the-art results on LFW, IJB-A, YouTube Faces, and CACD datasets.

Demonstrates excellent generalization capabilities across diverse face recognition datasets.

Simplifies face recognition training by using a residual CNN with normalized features.

Abstract

Face recognition (FR) methods report significant performance by adopting the convolutional neural network (CNN) based learning methods. Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs. Incorporating these tasks obviously requires additional efforts. Moreover, it demotivates the discovery of efficient CNN models for FR which are trained only with identity labels. We focus on this fact and propose an easily trainable and single CNN based FR method. Our CNN model exploits the residual learning framework. Additionally, it uses normalized features to compute the loss. Our extensive experiments show excellent generalization on different datasets. We obtain very competitive and state-of-the-art results on the LFW, IJB-A, YouTube faces and CACD datasets.