Mitigating Domain Mismatch in Face Recognition Using Style Matching

02/26/2021
by   Chun-Hsien Lin, et al.
0

Despite outstanding performance on public benchmarks, face recognition still suffers due to domain mismatch between training (source) and testing (target) data. Furthermore, these domains are not shared classes, which complicates domain adaptation. Since this is also a fine-grained classification problem which does not strictly follow the low-density separation principle, conventional domain adaptation approaches do not resolve these problems. In this paper, we formulate domain mismatch in face recognition as a style mismatch problem for which we propose two methods. First, we design a domain discriminator with human-level judgment to mine target-like images in the training data to mitigate the domain gap. Second, we extract style representations in low-level feature maps of the backbone model, and match the style distributions of the two domains to find a common style representation. Evaluations on verification and open-set and closed-set identification protocols show that both methods yield good improvements, and that performance is more robust if they are combined. Our approach is competitive with related work, and its effectiveness is verified in a practical application.

READ FULL TEXT

page 1

page 6

research
08/07/2017

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Despite rapid advances in face recognition, there remains a clear gap be...
research
05/23/2023

Adaptive Face Recognition Using Adversarial Information Network

In many real-world applications, face recognition models often degenerat...
research
05/27/2022

Deep face recognition with clustering based domain adaptation

Despite great progress in face recognition tasks achieved by deep convol...
research
02/26/2021

Domain Adapting Ability of Self-Supervised Learning for Face Recognition

Although deep convolutional networks have achieved great performance in ...
research
07/20/2022

Controllable and Guided Face Synthesis for Unconstrained Face Recognition

Although significant advances have been made in face recognition (FR), F...
research
02/27/2020

Reducing Geographic Performance Differential for Face Recognition

As face recognition algorithms become more accurate and get deployed mor...
research
03/28/2020

One-Shot Domain Adaptation For Face Generation

In this paper, we propose a framework capable of generating face images ...

Please sign up or login with your details

Forgot password? Click here to reset