Conference proceeding
Controllable and Guided Face Synthesis for Unconstrained Face Recognition
COMPUTER VISION, ECCV 2022, PT XII, v 13672, pp 701-719
01 Jan 2022
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Although significant advances have been made in face recognition (FR), FR in unconstrained environments remains challenging due to the domain gap between the semi-constrained training datasets and unconstrained testing scenarios. To address this problem, we propose a controllable face synthesis model (CFSM) that can mimic the distribution of target datasets in a style latent space. CFSM learns a linear subspace with orthogonal bases in the style latent space with precise control over the diversity and degree of synthesis. Furthermore, the pre-trained synthesis model can be guided by the FR model, making the resulting images more beneficial for FR model training. Besides, target dataset distributions are characterized by the learned orthogonal bases, which can be utilized to measure the distributional similarity among face datasets. Our approach yields significant performance gains on unconstrained benchmarks, such as IJB-B, IJB-C, TinyFace and IJB-S (+5.76% Rank1). Code is available at http://cylab.cse.msu.edu/project-ctsm.html.
Metrics
Details
- Title
- Controllable and Guided Face Synthesis for Unconstrained Face Recognition
- Creators
- Feng Liu - Drexel University, Computer Science (Computing)Minchul Kim - Michigan State UniversityAnil Jain - Michigan State UniversityXiaoming Liu - Michigan State University
- Publication Details
- COMPUTER VISION, ECCV 2022, PT XII, v 13672, pp 701-719
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer Nature
- Number of pages
- 19
- Grant note
- 2022-21102100004 / Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Web of Science ID
- WOS:000897093900041
- Scopus ID
- 2-s2.0-85142672081
- Other Identifier
- 991022008295604721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Imaging Science & Photographic Technology