Vec2Face: Unveil Human Faces From Their Blackbox Features in Face Recognition

Chi Nhan Duong, Thanh-Dat Truong, Khoa Luu, Kha Gia Quach, Hung Bui, Kaushik Roy; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 6132-6141

Abstract


Unveiling face images of a subject given his/her high-level representations extracted from a blackbox Face Recognition engine is extremely challenging. It is because the limitations of accessible information from that engine including its structure and uninterpretable extracted features. This paper presents a novel generative structure with Bijective Metric Learning, namely Bijective Generative Adversarial Networks in a Distillation framework (DiBiGAN), for synthesizing faces of an identity given that person's features. In order to effectively address this problem, this work firstly introduces a bijective metric so that the distance measurement and metric learning process can be directly adopted in image domain for an image reconstruction task. Secondly, a distillation process is introduced to maximize the information exploited from the blackbox face recognition engine. Then a Feature-Conditional Generator Structure with Exponential Weighting Strategy is presented for a more robust generator that can synthesize realistic faces with ID preservation. Results on several benchmarking datasets including CelebA, LFW, AgeDB, CFP-FP against matching engines have demonstrated the effectiveness of DiBiGAN on both image realism and ID preservation properties.

Related Material


[pdf] [arXiv] [video]
[bibtex]
@InProceedings{Duong_2020_CVPR,
author = {Duong, Chi Nhan and Truong, Thanh-Dat and Luu, Khoa and Quach, Kha Gia and Bui, Hung and Roy, Kaushik},
title = {Vec2Face: Unveil Human Faces From Their Blackbox Features in Face Recognition},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}