Search Results for author: Sang Hyun Park

Found 19 papers, 7 papers with code

CAT: Contrastive Adapter Training for Personalized Image Generation

2 code implementations11 Apr 2024 Jae Wan Park, Sang Hyun Park, Jun Young Koh, Junha Lee, Min Song

Finally, we mention the possibility of CAT in the aspects of multi-concept adapter and optimization.

Consistent Character Generation

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

no code implementations21 Dec 2023 Soopil Kim, Sion An, Philip Chikontwe, Myeongkyun Kang, Ehsan Adeli, Kilian M. Pohl, Sang Hyun Park

In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints.

Anomaly Detection Segmentation +1

Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model

1 code implementation15 Dec 2022 Wei Peng, Ehsan Adeli, Tomas Bosschieter, Sang Hyun Park, Qingyu Zhao, Kilian M. Pohl

As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models.


Feature Re-calibration based Multiple Instance Learning for Whole Slide Image Classification

1 code implementation22 Jun 2022 Philip Chikontwe, Soo Jeong Nam, Heounjeong Go, Meejeong Kim, Hyun Jung Sung, Sang Hyun Park

Whole slide image (WSI) classification is a fundamental task for the diagnosis and treatment of diseases; but, curation of accurate labels is time-consuming and limits the application of fully-supervised methods.

Image Classification Multiple Instance Learning +1

CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification

no code implementations CVPR 2022 Philip Chikontwe, Soopil Kim, Sang Hyun Park

Few-shot classification is a challenging problem that aims to learn a model that can adapt to unseen classes given a few labeled samples.


Uncertainty-Aware Semi-Supervised Few Shot Segmentation

no code implementations18 Oct 2021 Soopil Kim, Philip Chikontwe, Sang Hyun Park

During inference, query segmentation is predicted using prototypes from both support and unlabeled images including low-level features of the query images.

Pseudo Label Segmentation

First Demonstration of the Korean eLoran Accuracy in a Narrow Waterway Using Improved ASF Maps

no code implementations18 Sep 2021 Woohyun Kim, Pyo-Woong Son, Sul Gee Park, Sang Hyun Park, Jiwon Seo

This letter briefly summarizes the efforts of South Korea to deploy an enhanced long-range navigation (eLoran) system, which is a terrestrial low-frequency radio navigation system that can complement GNSSs.

A Meta-Learning Approach for Medical Image Registration

no code implementations21 Apr 2021 Heejung Park, Gyeong Min Lee, Soopil Kim, Ga Hyung Ryu, Areum Jeong, Sang Hyun Park, Min Sagong

To quickly adapt to various tasks, the meta learner was updated to get close to the center of parameters which are fine-tuned for each registration task.

Image Registration Medical Image Registration +1

Self-Supervised Learning based CT Denoising using Pseudo-CT Image Pairs

no code implementations6 Apr 2021 Dongkyu Won, Euijin Jung, Sion An, Philip Chikontwe, Sang Hyun Park

The proposed ensemble noise model can generate realistic CT noise, and thus our method significantly improves the denoising performance existing denoising models trained by supervised- and self-supervised learning.

Image Denoising Self-Supervised Learning

Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing

no code implementations26 Mar 2021 Myeongkyun Kang, Philip Chikontwe, Miguel Luna, Kyung Soo Hong, June Hong Ahn, Sang Hyun Park

Our experiments show that classifiers trained with de-biased generated images report improved in-distribution performance and generalization on an external COVID-19 dataset.

Computed Tomography (CT)

Graphene plasmon-phonon coupled modes at the exceptional point

no code implementations7 Dec 2020 Sang Hyun Park, Shengxuan Xia, Sang-Hyun Oh, Phaedon Avouris, Tony Low

Properties of graphene plasmons are greatly affected by their coupling to phonons.

Mesoscale and Nanoscale Physics

Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation

no code implementations19 Nov 2020 Soopil Kim, Sion An, Philip Chikontwe, Sang Hyun Park

In this paper, we propose a 3D few shot segmentation framework for accurate organ segmentation using limited training samples of the target organ annotation.

Few-Shot Learning Image Segmentation +5

Multiple Instance Learning with Center Embeddings for Histopathology Classification

1 code implementation29 Sep 2020 Philip Chikontwe, Meejeong Kim, Soo Jeong Nam, Heounjeong Go, Sang Hyun Park

To address this, recent methods have considered WSI classification as a Multiple Instance Learning (MIL) problem often with a multi-stage process for learning instance and slide level features.

Classification General Classification +4

Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification

no code implementations3 Mar 2020 Sion An, Soopil Kim, Philip Chikontwe, Sang Hyun Park

In addition to the unified learning of feature similarity and a few shot classifier, our method leads to emphasize informative features in support data relevant to the query data, which generalizes better on unseen subjects.

Autonomous Driving Classification +4

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