Inverting face embeddings with convolutional neural networks

Abstract

Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather than simply recognize them. In this work we use neural networks to effectively invert low-dimensional face embeddings while producing realistically looking consistent images. Our contribution is twofold, first we show that a gradient ascent style approaches can be used to reproduce consistent images, with a help of a guiding image. Second, we demonstrate that we can train a separate neural network to effectively solve the minimization problem in one pass, and generate images in real-time. We then evaluate the loss imposed by using a neural network instead of the gradient descent by comparing the final values of the minimized loss function.

References in corpus (2)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• DRAW: A Recurrent Neural Network For Image Generation

Cited by in corpus (11)

• Unsupervised Cross-Domain Image Generation
• On the Reconstruction of Face Images from Deep Face Templates
• Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques
• Towards Protecting Face Embeddings in Mobile Face Verification Scenarios
• HINNPerf: Hierarchical Interaction Neural Network for Performance Prediction of Configurable Systems
• Recent Progress of Face Image Synthesis
• Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
• Approximating Optimal Morphing Attacks using Template Inversion
• Fuzzy Commitments Offer Insufficient Protection to Biometric Templates Produced by Deep Learning
• DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning
• Attention-based Residual Speech Portrait Model for Speech to Face Generation