Research
I'm a machine learning and computer vision researcher working on various topics including adversarial attacks and defenses,
object detection, GANs, face recognition, image restoration, and segmentation.
|
|
GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
Pirazh Khorramshahi*,
Hossein Souri*,
Rama Chellappa,
Soheil Feizi
arXiv, 2020
PDF /
arXiv /
bibtex
GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution.
To tackle this issue, we take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
We call this approach GANs with Variational Entropy Regularizers (GAN+VER).
|
|
An adversarial learning algorithm for mitigating gender bias in face recognition
Prithviraj Dhar*,
Joshua Gleason*,
Hossein Souri,
Carlos D. Castillo,
Rama Chellappa
arXiv, 2020
PDF /
arXiv /
bibtex
A novel approach called `Adversarial Gender De-biasing (AGD)' to reduce the strength of gender information in face recognition features.
|
|
ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
Chun Pong Lau,
Hossein Souri,
Rama Chellappa
FG, 2019   (Oral Presentation)
PDF /
arXiv /
bibtex
In this work we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image.
|
Research Experience
- Research Assistant, Johns Hopkins University, Aug 2020 - Present
- Research Assistant, University of Maryland, 2018 - 2020
- Research Assistant, University of Tehran, 2016 - 2018
- Internship, Computer Networks Lab, University of Tehran, Summer 2016
|
Teaching Experience
- Teaching Assistant, Johns Hopkins University, Spring 2021
- Teaching Assistant, University of Maryland, College Park, Fall 2018 - Spring 2019
- Teaching Assistant, University of Tehran, 2015 - 2018
|
|