Towards Robust Face Recognition with Comprehensive Search

by   Manyuan Zhang, et al.
SenseTime Corporation
The Chinese University of Hong Kong

Data cleaning, architecture, and loss function design are important factors contributing to high-performance face recognition. Previously, the research community tries to improve the performance of each single aspect but failed to present a unified solution on the joint search of the optimal designs for all three aspects. In this paper, we for the first time identify that these aspects are tightly coupled to each other. Optimizing the design of each aspect actually greatly limits the performance and biases the algorithmic design. Specifically, we find that the optimal model architecture or loss function is closely coupled with the data cleaning. To eliminate the bias of single-aspect research and provide an overall understanding of the face recognition model design, we first carefully design the search space for each aspect, then a comprehensive search method is introduced to jointly search optimal data cleaning, architecture, and loss function design. In our framework, we make the proposed comprehensive search as flexible as possible, by using an innovative reinforcement learning based approach. Extensive experiments on million-level face recognition benchmarks demonstrate the effectiveness of our newly-designed search space for each aspect and the comprehensive search. We outperform expert algorithms developed for each single research track by large margins. More importantly, we analyze the difference between our searched optimal design and the independent design of the single factors. We point out that strong models tend to optimize with more difficult training datasets and loss functions. Our empirical study can provide guidance in future research towards more robust face recognition systems.


Loss Function Search for Face Recognition

In face recognition, designing margin-based (e.g., angular, additive, ad...

AirFace:Lightweight and Efficient Model for Face Recognition

With the development of convolutional neural network, significant progre...

WebFace260M: A Benchmark for Million-Scale Deep Face Recognition

Face benchmarks empower the research community to train and evaluate hig...

Robust RGB-D Face Recognition Using Attribute-Aware Loss

Existing convolutional neural network (CNN) based face recognition algor...

Towards Interpretable Face Recognition

Deep CNNs have been pushing the frontier of visual recognition over past...

Towards Flops-constrained Face Recognition

Large scale face recognition is challenging especially when the computat...

Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

Racial equality is an important theme of international human rights law,...

Please sign up or login with your details

Forgot password? Click here to reset