activity
20172022
most citedS-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima

5 citations · 17 across the 10 of their papers we have counts for

collaborators

20 papers

cs.CV20224 cited

Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition

Sungho Shin, Joosoon Lee, Junseok Lee +2

Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention si…

math.OC2022

Condensed interior-point methods: porting reduced-space approaches on GPU hardware

François Pacaud, Sungho Shin, Michel Schanen +2

The interior-point method (IPM) has become the workhorse method for nonlinear programming. The performance of IPM is directly related to the linear solver employed to factorize the…

q-bio.QM20201 cited

SBML2Julia: interfacing SBML with efficient nonlinear Julia modelling and solution tools for parameter optimization

Paul F. Lang, Sungho Shin, Victor M. Zavala

Motivation: Estimating model parameters from experimental observations is one of the key challenges in systems biology and can be computationally very expensive. While the Julia pr…

cs.LG2020

Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks

Yoonho Boo, Sungho Shin, Jungwook Choi +1

The quantization of deep neural networks (QDNNs) has been actively studied for deployment in edge devices. Recent studies employ the knowledge distillation (KD) method to improve t…

cs.LG2020

Multiple Classification with Split Learning

Jongwon Kim, Sungho Shin, Yeonguk Yu +2

Privacy issues were raised in the process of training deep learning in medical, mobility, and other fields. To solve this problem, we present privacy-preserving distributed deep le…

cs.LG20205 cited

S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima

Wonyong Sung, Iksoo Choi, Jinhwan Park +2

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss…