DeepAI AI Chat
Log In Sign Up

Inter-class Discrepancy Alignment for Face Recognition

by   Jiaheng Liu, et al.

The field of face recognition (FR) has witnessed great progress with the surge of deep learning. Existing methods mainly focus on extracting discriminative features, and directly compute the cosine or L2 distance by the point-to-point way without considering the context information. In this study, we make a key observation that the local con-text represented by the similarities between the instance and its inter-class neighbors1plays an important role forFR. Specifically, we attempt to incorporate the local in-formation in the feature space into the metric, and pro-pose a unified framework calledInter-class DiscrepancyAlignment(IDA), with two dedicated modules, Discrepancy Alignment Operator(IDA-DAO) andSupport Set Estimation(IDA-SSE). IDA-DAO is used to align the similarity scores considering the discrepancy between the images and its neighbors, which is defined by adaptive support sets on the hypersphere. For practical inference, it is difficult to acquire support set during online inference. IDA-SSE can provide convincing inter-class neighbors by introducing virtual candidate images generated with GAN. Further-more, we propose the learnable IDA-SSE, which can implicitly give estimation without the need of any other images in the evaluation process. The proposed IDA can be incorporated into existing FR systems seamlessly and efficiently. Extensive experiments demonstrate that this frame-work can 1) significantly improve the accuracy, and 2) make the model robust to the face images of various distributions.Without bells and whistles, our method achieves state-of-the-art performance on multiple standard FR benchmarks.


Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition

Current face recognition tasks are usually carried out on high-quality f...

Robust Face Anti-Spoofing with Dual Probabilistic Modeling

The field of face anti-spoofing (FAS) has witnessed great progress with ...

Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition

Face recognition for visible light (VIS) images achieve high accuracy th...

SphereFace Revived: Unifying Hyperspherical Face Recognition

This paper addresses the deep face recognition problem under an open-set...

DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition

Deep learning-based domain-invariant feature learning methods are advanc...

Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children

Despite the unprecedented improvement of face recognition, existing face...

Devil's in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID

Although Person Re-Identification has made impressive progress, difficul...