activity
20182022
most citedJointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domains

2 citations · 3 across the 3 of their papers we have counts for

collaborators

9 papers

cs.CV2022

Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization

Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

We propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN). Zero-sho…

cs.CV20221 cited

Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks

Sijia Wang, Yoojin Choi, Junya Chen +2

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. H…

cs.CV2021

Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay

Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

This paper proposes two novel knowledge transfer techniques for class-incremental learning (CIL). First, we propose data-free generative replay (DF-GR) to mitigate catastrophic for…

cs.CV2020

Data-Free Network Quantization With Adversarial Knowledge Distillation

Yoojin Choi, Jihwan Choi, Mostafa El-Khamy +1

Network quantization is an essential procedure in deep learning for development of efficient fixed-point inference models on mobile or edge platforms. However, as datasets grow lar…

eess.IV2019

Variable Rate Deep Image Compression With a Conditional Autoencoder

Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

In this paper, we propose a novel variable-rate learned image compression framework with a conditional autoencoder. Previous learning-based image compression methods mostly require…

cs.CV20192 cited

Jointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domains

Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional…