Soroush Abbasi Koohpayegani

soroush @ umbc.edu
soroush @ ucdavis.edu
Google Scholar

Please use a browser that supports "canvas"

About Me

I am a 5th year PhD student in computer science at University of California Davis, advised by Hamed Pirsiavash. Before this, I got my BS in computer science from Sharif University of Technology. Get my CV. My research is about machine learning, computer vision. In particular, I am intrested in self-supervised learning, multimodal models (e.g., language and vision) and efficient Deep Learning Models.
I believe human language is ambiguous and a limited representation to express latent space of my mind. Therefore, I don't particularly prefer using human language to express my thoughts. Conversely, I find images to be more informative. That's why I rely on Generative AI to capture the images in my mind and bring them to life. You are welcome to visit the latent space of my mind.

Papers

2024
 SlowFormer: Universal Adversarial Patch for Attack on Compute
and Energy Efficiency of Inference Efficient Vision Transformers
KL Navaneet*, Soroush Abbasi Koohpayegani*, Essam Sleiman*, Hamed Pirsiavash *equal contribution
CVPR 2024 .
[PDF][Code]
NOLA: Networks as Linear Ccombinatotion of Low Rank Random Basis
Soroush Abbasi Koohpayegani*, KL Navaneet*
Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash *equal contribution
ICLR 2024 .
[PDF][Code]
SimA: Simple Softmax-free Attention for Vision Transformers
Soroush Abbasi Koohpayegani, Hamed Pirsiavash
WACV 2024 .
[PDF][Code]
A Closer Look at Robustness of Vision Transformers to Backdoor Attacks
Akshayvarun Subramanya, Soroush Abbasi Koohpayegani*, Aniruddha Saha*
Ajinkya Tejankar, Hamed Pirsiavash *equal contribution
WACV 2024.
[PDF][Code]
2023
 Multi-Agent Lifelong Implicit Neural Learning
Soheil Kolouri, Ali Abbasi, Soroush Abbasi Koohpayegani, Parsa Nooralinejad, Hamed Pirsiavash
IEEE Signal Processing Letters .
[PDF]
Compact3D: Compressing Gaussian Splat Radiance Field Models with Vector Quantization
KL Navaneet*, Kossar Pourahmadi Meibodi*, Soroush Abbasi Koohpayegani, Hamed Pirsiavash *equal contribution
arXiv 2023 .
[PDF][Code]
GeNIe: Generative Hard Negative Images Through Diffusion
Soroush Abbasi Koohpayegani, Anuj Singh, K L Navaneet, Hadi Jamali-Rad, Hamed Pirsiavash
arXiv 2023 .
[PDF][Code]
PRANC: Pseudo RAndom Networks for Compacting deep models
Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani*
Kossar Pourahmadi Meibodi*, Rana Muhammad Shahroz Khan*, Soheil Kolouri, Hamed Pirsiavash
ICCV 2023 .
[PDF][Code]
2022
 ATS: Adaptive Token Sampling for Efficient Vision Transformers
Mohsen Fayyaz*, Soroush Abbasi Koohpayegani*, Farnoush Rezaei Jafari*, Sunando Sengupta,
Hamid Reza Vaezi Joze, Eric Sommerlade, Hamed Pirsiavash, Juergen Gall *equal contribution
ECCV 2022 (Oral presentation).
[PDF][Code]
Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning
KL Navaneet*, Soroush Abbasi Koohpayegani*, Ajinkya Tejankar*,
Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash *equal contribution
ECCV 2022 .
[PDF][Code]
Backdoor Attacks on Self-Supervised Learning
Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
CVPR 2022 (Oral presentation).
[PDF][Code]
Consistent Explanations by Contrastive Learning
Vipin Pillai, Soroush Abbasi Koohpayegani, Ashley Ouligian, Dennis Fong, Hamed Pirsiavash
CVPR 2022 .
[PDF][Code]
2021
 Mean Shift for Self-Supervised Learning
Soroush Abbasi Koohpayegani*, Ajinkya Tejankar*, Hamed Pirsiavash *equal contribution
ICCV 2021 (Oral presentation).
[PDF][Project Page][Code]
ISD: Self-Supervised Learning by Iterative Similarity Distillation
Ajinkya Tejankar*, Soroush Abbasi Koohpayegani*, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash *equal contribution
ICCV 2021 .
[PDF][Project Page][Code]
SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation
KL Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash
BMVC 2021 .
[PDF][Code]
2020
 CompRess: Self-Supervised Learning by Compressing Representations
Soroush Abbasi Koohpayegani*, Ajinkya Tejankar*, Hamed Pirsiavash *equal contribution
NeurIPS 2020.
[PDF][Project Page][Code]

Experience

 Apple
Computer Vision Research Internship

Summer 2022
University of California, Davis
Research Assistant
(Supervisor: Hamed Pirsiavash)

Sep 2022 - Present
Microsoft
Computer Vision Research Internship

Summer 2021 - Applied Sciences Group
University of Maryland, Baltimore County
Research Assistant
(Supervisor: Hamed Pirsiavash)

Aug 2019 - May 2022
BasirTech
Computer Vision Research Engineer
(Supervisor: Mostafa Kamali Tabrizi)

May 2018 - Aug 2019

Education

 University of California, Davis
Ph.D. Computer Science

(Aug 2022 - Present)
 University of Maryland, Baltimore County
Master's Computer Science

(Aug 2019 - Aug 2022)
 Sharif University of Technology
B.Sc. Computer Science

(Aug 2013 - Feb 2018)

Contacts