no code implementations • 3 Jan 2024 • Xingxing Zuo, Pouya Samangouei, Yunwen Zhou, Yan Di, Mingyang Li
This is achieved by distilling feature maps generated from image-based foundation models into those rendered from our 3D model.
no code implementations • ICLR 2020 • Igor Lovchinsky, Alon Daks, Israel Malkin, Pouya Samangouei, Ardavan Saeedi, Yang Liu, Swami Sankaranarayanan, Tomer Gafner, Ben Sternlieb, Patrick Maher, Nathan Silberman
In most machine learning tasks unambiguous ground truth labels can easily be acquired.
1 code implementation • 23 Nov 2019 • Wei-An Lin, Yogesh Balaji, Pouya Samangouei, Rama Chellappa
Additionally, we show how InvGAN can be used to implement reparameterization white-box attacks on projection-based defense mechanisms.
no code implementations • ECCV 2018 • Pouya Samangouei, Ardavan Saeedi, Liam Nakagawa, Nathan Silberman
We introduce a new method for interpreting computer vision models: visually perceptible, decision-boundary crossing transformations.
5 code implementations • ICLR 2018 • Pouya Samangouei, Maya Kabkab, Rama Chellappa
Defense-GAN is trained to model the distribution of unperturbed images.
Ranked #1 on Adversarial Defense against FGSM Attack on MNIST
Adversarial Defense Adversarial Defense against FGSM Attack +1
1 code implementation • 14 Mar 2018 • Pouya Samangouei, Mahyar Najibi, Larry Davis, Rama Chellappa
In this paper, we introduce the Face Magnifier Network (Face-MageNet), a face detector based on the Faster-RCNN framework which enables the flow of discriminative information of small scale faces to the classifier without any skip or residual connections.
1 code implementation • 5 Feb 2018 • Maya Kabkab, Pouya Samangouei, Rama Chellappa
We propose to train the GANs in a task-aware fashion, specifically for reconstruction tasks.
6 code implementations • ICCV 2017 • Mahyar Najibi, Pouya Samangouei, Rama Chellappa, Larry Davis
Surprisingly, with a headless VGG-16, SSH beats the ResNet-101-based state-of-the-art on the WIDER dataset.
no code implementations • 29 Apr 2016 • Pouya Samangouei, Rama Chellappa
We present a Deep Convolutional Neural Network (DCNN) architecture for the task of continuous authentication on mobile devices.