AIConfPaper
← Search

Soroush Abbasi Koohpayegani

12 accepted papers

2025

MCNC: Manifold-Constrained Reparameterization for Neural Compression

Chayne Thrash, Reed Andreas, Ali Abbasi, Parsa Nooralinejad, Soroush Abbasi Koohpayegani, Hamed Pirsiavash +1
ICLR 2025poster

The outstanding performance of large foundational models across diverse tasks, from computer vision to speech and natural language processing, has significantly increased their demand. However, storing and transmitting these models poses significant challenges due to their massive size (e.g., 750GB…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization

K L Navaneet*, Kossar Pourahmadi Meibodi, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
ECCV 2024poster

"3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the pa…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2024

NOLA: Compressing LoRA using Linear Combination of Random Basis

Soroush Abbasi Koohpayegani, Navaneet K L, Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash
ICLR 2024poster

Fine-tuning Large Language Models (LLMs) and storing them for each downstream task or domain is impractical because of the massive model size (e.g., 350GB in GPT-3). Current literature, such as LoRA, showcases the potential of low-rank modifications to the original weights of an LLM, enabling effici…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2024

SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers

K L Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman, Hamed Pirsiavash
CVPR 2024poster

Recently there has been a lot of progress in reducing the computation of deep models at inference time. These methods can reduce both the computational needs and power usage of deep models. Some of these approaches adaptively scale the compute based on the input instance. We show that such models ca…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

PRANC: Pseudo RAndom Networks for Compacting Deep Models

Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani, Kossar Pourahmadi Meibodi, Rana Muhammad Shahroz Khan, Soheil Kolouri +1
ICCV 2023poster

We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space. During training, we seek local minima that reside within the subspace spanned by these random models (i.e., `basis' networks). Our framework, PRA…

Cited by 12PDF ↗code ↗Scholar ↗
2022

Adaptive Token Sampling for Efficient Vision Transformers

Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari, Sunando Sengupta, Hamid Reza Vaezi Joze, Eric Sommerlade +2
ECCV 2022poster

"While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs of a vision transformer can be decreased by reducing the number of tokens in the network, there is no setting that is o…

Cited by 231Source ↗PDF ↗code ↗Scholar ↗
2022

Backdoor Attacks on Self-Supervised Learning

Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
CVPR 2022oral

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random c…

Cited by 133PDF ↗code ↗Scholar ↗
2022

Consistent Explanations by Contrastive Learning

Vipin Pillai, Soroush Abbasi Koohpayegani, Ashley Ouligian, Dennis Fong, Hamed Pirsiavash
CVPR 2022poster

Post-hoc explanation methods, e.g., Grad-CAM, enable humans to inspect the spatial regions responsible for a particular network decision. However, it is shown that such explanations are not always consistent with human priors, such as consistency across image transformations. Given an interpretation…

Cited by 25PDF ↗code ↗Scholar ↗
2022

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning

K L Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash
ECCV 2022poster

"We are interested in representation learning in self-supervised, supervised, and semi-supervised settings. Some recent self-supervised learning methods like mean-shift (MSF) cluster images by pulling the embedding of a query image to be closer to its nearest neighbors (NNs). Since most NNs are clos…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2021

ISD: Self-Supervised Learning by Iterative Similarity Distillation

Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash
ICCV 2021poster

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to pull two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not all negative images are equally negative. Hence, we introduc…

Cited by 66PDF ↗code ↗Scholar ↗
2020

CompRess: Self-Supervised Learning by Compressing Representations

Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash
NeurIPS 2020poster

Self-supervised learning aims to learn good representations with unlabeled data. Recent works have shown that larger models benefit more from self-supervised learning than smaller models. As a result, the gap between supervised and self-supervised learning has been greatly reduced for larger models.…

Cited by 113Source ↗PDF ↗code ↗Scholar ↗