Projects and Code

Exploring the Connection between Robust and Generative Models Repository of the paper "Exploring the Connection between Robust and Generative Models"(https://arxiv.org/abs/2304.04033) About The Project We offer a study that connects robust discriminative classifiers trained with adversarial training (AT) with generative modeling in the form of Energy-based Models (EBM).

Official Pytorch implementation of the following paper: Rouhsedaghat M, Monajatipoor M, Kuo CC, Masi I. MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier In Proceedings of AAAI Conference on Artificial Intelligence AAAI-23.

For method details, please refer to the paper, the video presentation, demo of the system Deepfake detection in videos. The figure shows our system predic- tions when trained only on FaceForensics++ for a fake video “in the wild” (left) and its pristine video (right).

This is the official repo for the Structure via Consensus for Face Segmentation and Parsing (CVPR 2020). For method details, please refer to the paper and the supplementary material.

Deep Face Recognition: A Tutorial Abstract Face recognition made tremendous leaps in the last five years with a myriad of systems proposing novel techniques substantially backed by deep convolutional neural networks (DCNN).