no code implementations • 21 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.
1 code implementation • 22 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.
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.
no code implementations • 18 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.
no code implementations • 15 Oct 2021 • Myeongkyun Kang, Dongkyu Won, Miguel Luna, Philip Chikontwe, Kyung Soo Hong, June Hong Ahn, Sang Hyun Park
Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model.
no code implementations • 6 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.
no code implementations • 26 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.
no code implementations • 19 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.
1 code implementation • 29 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.
no code implementations • 3 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.