Search Results - "Jang, Donggon"

A Multiple‐State Ion Synaptic Transistor Applicable to Abnormal Car Detection with Transfer Learning by Yu, Ji-Man, Ham, Gyeongdo, Lee, Chungryeol, Lee, Jae-Hyeok, Han, Joon-Kyu, Kim, Jin-Ki, Jang, Donggon, Kim, Nahyun, Kim, Moon-Seok, Im, Sung Gap, Kim, Dae-Shik, Choi, Yang-Kyu

“…An artificial synapse is an essential element to construct a hardware‐based artificial neural network (ANN). While various synaptic devices have been proposed…”
Get full text

Maximizing discrimination capability of knowledge distillation with energy function by Kim, Seonghak, Ham, Gyeongdo, Lee, Suin, Jang, Donggon, Kim, Daeshik

“…To apply the latest computer vision techniques that require a large computational cost in real industrial applications, knowledge distillation methods (KDs)…”
Get full text

Energy-Based Domain Adaptation Without Intermediate Domain Dataset for Foggy Scene Segmentation by Jang, Donggon, Lee, Sunhyeok, Choi, Gyuwon, Lee, Yejin, Son, Sanghyeok, Kim, Dae-Shik

“…Robust segmentation performance under dense fog is crucial for autonomous driving, but collecting labeled real foggy scene datasets is burdensome in the real…”
Get full text

Learning Color Representations for Low-Light Image Enhancement by Kim, Bomi, Lee, Sunhyeok, Kim, Nahyun, Jang, Donggon, Kim, Dae-Shik

“…Color conveys important information about the visible world. However, under low-light conditions, both pixel intensity, as well as true color distribution, can…”
Get full text

Strengthening the Transferability of Adversarial Examples Using Advanced Looking Ahead and Self-CutMix by Jang, Donggon, Son, Sanghyeok, Kim, Dae-Shik

“…Deep neural networks (DNNs) are vulnerable to adversarial examples generated by adding malicious noise imperceptible to a human. The adversarial examples…”
Get full text

Maximizing Discrimination Capability of Knowledge Distillation with Energy Function by Kim, Seonghak, Ham, Gyeongdo, Lee, Suin, Jang, Donggon, Kim, Daeshik

“…To apply the latest computer vision techniques that require a large computational cost in real industrial applications, knowledge distillation methods (KDs)…”
Get full text

Temporally Averaged Regression for Semi-Supervised Low-Light Image Enhancement by Lee, Sunhyeok, Jang, Donggon, Kim, Dae-Shik

“…Constructing annotated paired datasets for low-light image enhancement is complex and time-consuming, and existing deep learning models often generate noisy…”
Get full text

Unsupervised Image Denoising with Frequency Domain Knowledge by Kim, Nahyun, Jang, Donggon, Lee, Sunhyeok, Kim, Bomi, Kim, Dae-Shik

“…Supervised learning-based methods yield robust denoising results, yet they are inherently limited by the need for large-scale clean/noisy paired datasets. The…”
Get full text