Twitter |
Google Scholar |
Semantic Scholar |
GitHub
About Me
I am a Ph.D. Electrical Engineer student at Technion, researching Deep Learning and Computer Vision under the supervision of Prof. Michael Elad. I am interested in adversarial attacks and robustness and in generative models. I am also a computer vision research intern at Amazon.
Prior my Ph.D. studies, I obtained my B.Sc. in EE from the Technion (cum laude) and worked as a chip design intern at Apple.
Publications
CLIPAG: Towards Generator-Free Text-to-Image Generation
Roy Ganz, Michael Elad
WACV 2024, in IEEE/CVF Winter Conference on Applications of Computer Vision.
FuseCap: Leveraging Large Language Models to Fuse Visual Data into Enriched Image Captions
Noam Rotstein, David Bensaid, Shaked Brody, Roy Ganz, Ron Kimmel
Preprint, arXiv:2305.17718.
[Code]Do Perceptually Aligned Gradients Imply Adversarial Robustness?
Roy Ganz, Bahjat Kawar, Michael Elad
ICML 2023 oral presentation, in International Conference on Machine Learning.
[Code]Towards Models that Can See and Read
Roy Ganz, Oren Nuriel, Aviad Aberdam, Yair Kittenplon, Shai Mazor, Ron Litman
ICCV 2023, in International Conference on Computer Vision.
CLIPTER: Looking at the Bigger Picture in Scene Text Recognition
Aviad Aberdam, David Bensaïd, Alona Golts, Roy Ganz, Oren Nuriel, Royee Tichauer, Shai Mazor, Ron Litman
ICCV 2023, in International Conference on Computer Vision.
Classifier Robustness Enhancement Via Test-Time Transformation
Tsachi Blau, Roy Ganz, Chaim Baskin, Michael Elad, Alex Bronstein
Preprint, arXiv:2303.15409.
Enhancing diffusion-based image synthesis with robust classifier guidance
Bahjat Kawar, Roy Ganz, Michael Elad
TMLR 2023, in Transactions on Machine Learning Research.
[Code]BIGRoC: Boosting Image Generation via a Robust Classifier
Roy Ganz, Michael Elad
TMLR 2023, in Transactions on Machine Learning Research.
[Code]Threat model-agnostic adversarial defense using diffusion models
Tsachi Blau, Roy Ganz, Bahjat Kawar, Alex Bronstein, Michael Elad
Preprint, arXiv:2207.08089.
Multimodal semi-supervised learning for text recognition
Aviad Aberdam, Roy Ganz, Shai Mazor, Ron Litman
Preprint, arXiv:2205.03873.
Improved Image Generation via Sparse Modeling
Roy Ganz, Michael Elad
ICLR Workshop on Deep Generative Models for Highly Structured Data.