# Towards End-to-End Face Recognition through Alignment Learning

## TL;DR

This paper proposes an end-to-end face recognition approach that automatically learns facial alignment within a CNN using spatial transformer layers, eliminating the need for prior landmark knowledge and improving accuracy.

## Contribution

It introduces a novel method integrating alignment learning into CNNs for face recognition, removing reliance on predefined facial landmarks.

## Key findings

- Achieved 99.08% verification accuracy on LFW dataset.
- Demonstrated the effectiveness of learned alignment in end-to-end face recognition.
- Comparable performance to state-of-the-art methods.

## Abstract

Plenty of effective methods have been proposed for face recognition during the past decade. Although these methods differ essentially in many aspects, a common practice of them is to specifically align the facial area based on the prior knowledge of human face structure before feature extraction. In most systems, the face alignment module is implemented independently. This has actually caused difficulties in the designing and training of end-to-end face recognition models. In this paper we study the possibility of alignment learning in end-to-end face recognition, in which neither prior knowledge on facial landmarks nor artificially defined geometric transformations are required. Specifically, spatial transformer layers are inserted in front of the feature extraction layers in a Convolutional Neural Network (CNN) for face recognition. Only human identity clues are used for driving the neural network to automatically learn the most suitable geometric transformation and the most appropriate facial area for the recognition task. To ensure reproducibility, our model is trained purely on the publicly available CASIA-WebFace dataset, and is tested on the Labeled Face in the Wild (LFW) dataset. We have achieved a verification accuracy of 99.08\% which is comparable to state-of-the-art single model based methods.