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

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 6131 - 6140
• Main Authors: Duong, Chi Nhan, Truong, Thanh-Dat, Luu, Khoa, Quach, Kha Gia, Bui, Hung, Roy, Kaushik
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2020
• Subjects: Engines; Face recognition; Feature extraction; Generators; Image reconstruction; Measurement; Task analysis
• ISSN: 1063-6919
• DOI: 10.1109/CVPR42600.2020.00617

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.