Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition

by   Chi Nhan Duong, et al.

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.


page 3

page 6

page 7


Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition

In this work, we investigate the problem of face reconstruction given a ...

Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network

With the broad use of face recognition, its weakness gradually emerges t...

Disentangled Face Identity Representations for joint 3D Face Recognition and Expression Neutralisation

In this paper, we propose a new deep learning-based approach for disenta...

smart application for AMS using Face Recognition

Attendance Management System (AMS) can be made into smarter way by using...

How Old Are You? Face Age Translation with Identity Preservation Using GANs

We present a novel framework to generate images of different age while p...

ID2image: Leakage of non-ID information into face descriptors and inversion from descriptors to images

Embedding a face image to a descriptor vector using a deep CNN is a wide...

KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network

In this paper, we propose a kinship generator network that can synthesiz...

Please sign up or login with your details

Forgot password? Click here to reset