activity
20202022
most citedSelf-Supervised Learning based CT Denoising using Pseudo-CT Image Pairs

6 citations · 18 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20224 cited

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

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. Recent approaches pre-train a feature extr…

cs.CV20216 cited

Uncertainty-Aware Semi-Supervised Few Shot Segmentation

Soopil Kim, Philip Chikontwe, Sang Hyun Park

Few shot segmentation (FSS) aims to learn pixel-level classification of a target object in a query image using only a few annotated support samples. This is challenging as it requi…

eess.IV20216 cited

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

Dongkyu Won, Euijin Jung, Sion An +2

Recently, Self-supervised learning methods able to perform image denoising without ground truth labels have been proposed. These methods create low-quality images by adding random…

eess.IV2021

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

Myeongkyun Kang, Philip Chikontwe, Miguel Luna +3

Following the pandemic outbreak, several works have proposed to diagnose COVID-19 with deep learning in computed tomography (CT); reporting performance on-par with experts. However…

cs.CV20202 cited

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

Soopil Kim, Sion An, Philip Chikontwe +1

Segmentation of organs of interest in 3D medical images is necessary for accurate diagnosis and longitudinal studies. Though recent advances using deep learning have shown success…

eess.SP2020

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

Sion An, Soopil Kim, Philip Chikontwe +1

Brain-Computer Interfaces (BCI) based on Electroencephalography (EEG) signals, in particular motor imagery (MI) data have received a lot of attention and show the potential towards…