activity
20172020
most citedAcceleration of Convolutional Neural Network Using FFT-Based Split Convolutions

25 citations · 49 across the 10 of their papers we have counts for

collaborators

19 papers

cs.LG2020

Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

Reza Esfandiarpoor, Amy Pu, Mohsen Hajabdollahi +1

In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose…

eess.IV2020

Classification of Diabetic Retinopathy Using Unlabeled Data and Knowledge Distillation

Sajjad Abbasi, Mohsen Hajabdollahi, Pejman Khadivi +4

Knowledge distillation allows transferring knowledge from a pre-trained model to another. However, it suffers from limitations, and constraints related to the two models need to be…

cs.MM2020

Hardware Implementation of Adaptive Watermarking Based on Local Spatial Disorder Analysis

Mohsen Hajabdolahi, Nader Karimi, Shahram Shirani +1

With the increasing use of the internet and the ease of exchange of multimedia content, the protection of ownership rights has become a significant concern. Watermarking is an effi…

cs.CV202025 cited

Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions

Kamran Chitsaz, Mohsen Hajabdollahi, Nader Karimi +2

Convolutional neural networks (CNNs) have a large number of variables and hence suffer from a complexity problem for their implementation. Different methods and techniques have dev…

cs.CV2020

Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer

Sajjad Abbasi, Mohsen Hajabdollahi, Nader Karimi +2

Convolutional neural networks (CNNs) are extensively beneficial for medical image processing. Medical images are plentiful, but there is a lack of annotated data. Transfer learning…

cs.CV20201 cited

Splitting Convolutional Neural Network Structures for Efficient Inference

Emad MalekHosseini, Mohsen Hajabdollahi, Nader Karimi +2

For convolutional neural networks (CNNs) that have a large volume of input data, memory management becomes a major concern. Memory cost reduction can be an effective way to deal wi…