849 citations · 1.1k across the 20 of their papers we have counts for
42 papers
SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers
KL Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman +1
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 de…
NOLA: Compressing LoRA using Linear Combination of Random Basis
Soroush Abbasi Koohpayegani, KL Navaneet, Parsa Nooralinejad +2
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 litera…
Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
Ajinkya Tejankar, Maziar Sanjabi, Qifan Wang +4
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the un…
A Cookbook of Self-Supervised Learning
Randall Balestriero, Mark Ibrahim, Vlad Sobal +16
Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art wi…
Is Multi-Task Learning an Upper Bound for Continual Learning?
Zihao Wu, Huy Tran, Hamed Pirsiavash +1
Continual and multi-task learning are common machine learning approaches to learning from multiple tasks. The existing works in the literature often assume multi-task learning as a…
Backdoor Attacks on Vision Transformers
Akshayvarun Subramanya, Aniruddha Saha, Soroush Abbasi Koohpayegani +2
Vision Transformers (ViT) have recently demonstrated exemplary performance on a variety of vision tasks and are being used as an alternative to CNNs. Their design is based on a sel…
SimA: Simple Softmax-free Attention for Vision Transformers
Soroush Abbasi Koohpayegani, Hamed Pirsiavash
Recently, vision transformers have become very popular. However, deploying them in many applications is computationally expensive partly due to the Softmax layer in the attention b…
PRANC: Pseudo RAndom Networks for Compacting deep models
Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani +4
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…
A Simple Approach to Adversarial Robustness in Few-shot Image Classification
Akshayvarun Subramanya, Hamed Pirsiavash
Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years. However, the classifiers are vulnerable t…
Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations
Ali Abbasi, Parsa Nooralinejad, Vladimir Braverman +2
Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep n…
Amenable Sparse Network Investigator
Saeed Damadi, Erfan Nouri, Hamed Pirsiavash
We present "Amenable Sparse Network Investigator" (ASNI) algorithm that utilizes a novel pruning strategy based on a sigmoid function that induces sparsity level globally over the…
SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation
K L Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar +1
Feature regression is a simple way to distill large neural network models to smaller ones. We show that with simple changes to the network architecture, regression can outperform m…
A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision
Ajinkya Tejankar, Maziar Sanjabi, Bichen Wu +4
Using natural language as a supervision for training visual recognition models holds great promise. Recent works have shown that if such supervision is used in the form of alignmen…
Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning
KL Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar +3
We are interested in representation learning in self-supervised, supervised, and semi-supervised settings. Some recent self-supervised learning methods like mean-shift (MSF) cluste…
MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification
Rex Liu, Huanle Zhang, Hamed Pirsiavash +1
We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification. MASTAF takes input from a general video spatial and temporal represe…
Adaptive Token Sampling For Efficient Vision Transformers
Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari +5
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…
Constrained Mean Shift for Representation Learning
Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
We are interested in representation learning from labeled or unlabeled data. Inspired by recent success of self-supervised learning (SSL), we develop a non-contrastive representati…
A Simple Baseline for Low-Budget Active Learning
Kossar Pourahmadi, Parsa Nooralinejad, Hamed Pirsiavash
Active learning focuses on choosing a subset of unlabeled data to be labeled. However, most such methods assume that a large subset of the data can be annotated. We are interested…
Consistent Explanations by Contrastive Learning
Vipin Pillai, Soroush Abbasi Koohpayegani, Ashley Ouligian +2
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 explanation…
Backdoor Attacks on Self-Supervised Learning
Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani +1
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 lear…
Mean Shift for Self-Supervised Learning
Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash
Most recent self-supervised learning (SSL) algorithms learn features by contrasting between instances of images or by clustering the images and then contrasting between the image c…
ISD: Self-Supervised Learning by Iterative Similarity Distillation
Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Vipin Pillai +2
Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared…
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Simon Ging, Mohammadreza Zolfaghari, Hamed Pirsiavash +1
Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics. In th…
CompRess: Self-Supervised Learning by Compressing Representations
Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash
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…