Search Results for author: Cheolkon Jung

Found 12 papers, 6 papers with code

WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazing

1 code implementation2 Apr 2024 Seongmin Hwang, Daeyoung Han, Cheolkon Jung, Moongu Jeon

In this paper, we introduce WaveDH, a novel and compact ConvNet designed to address this efficiency gap in image dehazing.

Image Dehazing Single Image Dehazing

SuperStyleNet: Deep Image Synthesis with Superpixel Based Style Encoder

1 code implementation17 Dec 2021 Jonghyun Kim, Gen Li, Cheolkon Jung, Joongkyu Kim

First, we directly extract the style codes from the original image based on superpixels to consider local objects.

Image Generation Superpixels

Edge and Identity Preserving Network for Face Super-Resolution

1 code implementation27 Aug 2020 Jonghyun Kim, Gen Li, Inyong Yun, Cheolkon Jung, Joongkyu Kim

In this paper, we propose a novel Edge and Identity Preserving Network for Face SR Network, named as EIPNet, to minimize the distortion by utilizing a lightweight edge block and identity information.


Frequency Pooling: Shift-Equivalent and Anti-Aliasing Down Sampling

no code implementations25 Sep 2019 Zhendong Zhang, Cheolkon Jung

Convolutional layer utilizes the shift-equivalent prior of images which makes it a great success for image processing.

GBDT-MO: Gradient Boosted Decision Trees for Multiple Outputs

3 code implementations10 Sep 2019 Zhendong Zhang, Cheolkon Jung

When there are multiple outputs, GBDT constructs multiple trees corresponding to the output variables.

Adversarial Defense by Suppressing High-frequency Components

1 code implementation19 Aug 2019 Zhendong Zhang, Cheolkon Jung, Xiaolong Liang

Recent works show that deep neural networks trained on image classification dataset bias towards textures.

Adversarial Defense Classification +3

Attention-Aware Linear Depthwise Convolution for Single Image Super-Resolution

no code implementations7 Aug 2019 Seongmin Hwang, Gwanghuyn Yu, Cheolkon Jung, Jin-Young Kim

Although deep convolutional neural networks (CNNs) have obtained outstanding performance in image superresolution (SR), their computational cost increases geometrically as CNN models get deeper and wider.

Image Super-Resolution

Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Study

no code implementations26 Feb 2019 Zhendong Zhang, Cheolkon Jung

However, the performance of an RC network is not satisfactory if we directly unroll the same kernels multiple steps.

Image Classification Model Compression +1

Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment

1 code implementation1 Oct 2018 Inyong Yun, Cheolkon Jung, Xinran Wang, Alfred O. Hero, Joongkyu Kim

Pedestrians in videos have a wide range of appearances such as body poses, occlusions, and complex backgrounds, and there exists the proposal shift problem in pedestrian detection that causes the loss of body parts such as head and legs.

Pedestrian Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.