Search Results for author: Jong Chul Ye

Found 138 papers, 50 papers with code

C-DARL: Contrastive diffusion adversarial representation learning for label-free blood vessel segmentation

no code implementations31 Jul 2023 Boah Kim, Yujin Oh, Bradford J. Wood, Ronald M. Summers, Jong Chul Ye

Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine.

Contrastive Learning Representation Learning

Generative AI for Medical Imaging: extending the MONAI Framework

2 code implementations27 Jul 2023 Walter H. L. Pinaya, Mark S. Graham, Eric Kerfoot, Petru-Daniel Tudosiu, Jessica Dafflon, Virginia Fernandez, Pedro Sanchez, Julia Wolleb, Pedro F. da Costa, Ashay Patel, Hyungjin Chung, Can Zhao, Wei Peng, Zelong Liu, Xueyan Mei, Oeslle Lucena, Jong Chul Ye, Sotirios A. Tsaftaris, Prerna Dogra, Andrew Feng, Marc Modat, Parashkev Nachev, Sebastien Ourselin, M. Jorge Cardoso

We have implemented these models in a generalisable fashion, illustrating that their results can be extended to 2D or 3D scenarios, including medical images with different modalities (like CT, MRI, and X-Ray data) and from different anatomical areas.

Anomaly Detection Denoising +2

Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models

1 code implementation16 Jun 2023 Geon Yeong Park, Jeongsol Kim, Beomsu Kim, Sang Wan Lee, Jong Chul Ye

Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment.

Denoising Image Inpainting

Unpaired Deep Learning for Pharmacokinetic Parameter Estimation from Dynamic Contrast-Enhanced MRI

no code implementations7 Jun 2023 Gyutaek Oh, Won-Jin Moon, Jong Chul Ye

DCE-MRI provides information about vascular permeability and tissue perfusion through the acquisition of pharmacokinetic parameters.

Direct Diffusion Bridge using Data Consistency for Inverse Problems

no code implementations31 May 2023 Hyungjin Chung, Jeongsol Kim, Jong Chul Ye

Diffusion model-based inverse problem solvers have shown impressive performance, but are limited in speed, mostly as they require reverse diffusion sampling starting from noise.

Score-based Diffusion Models for Bayesian Image Reconstruction

no code implementations25 May 2023 Michael T. McCann, Hyungjin Chung, Jong Chul Ye, Marc L. Klasky

This paper explores the use of score-based diffusion models for Bayesian image reconstruction.

Image Reconstruction

Data Topology-Dependent Upper Bounds of Neural Network Widths

no code implementations25 May 2023 Sangmin Lee, Jong Chul Ye

This is then extended to a simplicial complex, deriving width upper bounds based on its topological structure.

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

1 code implementation24 May 2023 Beomsu Kim, Gihyun Kwon, Kwanyoung Kim, Jong Chul Ye

In this work, we propose the Unpaired Neural Schr\"odinger Bridge (UNSB), which combines SB with adversarial training and regularization to learn a SB between unpaired data.

Image-to-Image Translation Translation

LLM Itself Can Read and Generate CXR Images

1 code implementation19 May 2023 Suhyeon Lee, Won Jun Kim, Jong Chul Ye

Building on the recent remarkable development of large language models (LLMs), active attempts are being made to extend the utility of LLMs to multimodal tasks.

Instruction Following

Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion

no code implementations15 Mar 2023 Inhwa Han, Serin Yang, Taesung Kwon, Jong Chul Ye

Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity.

Image Generation Image Manipulation

Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer

1 code implementation ICCV 2023 Serin Yang, Hyunmin Hwang, Jong Chul Ye

Diffusion models have shown great promise in text-guided image style transfer, but there is a trade-off between style transformation and content preservation due to their stochastic nature.

Image-to-Image Translation Style Transfer

Fast Diffusion Sampler for Inverse Problems by Geometric Decomposition

no code implementations10 Mar 2023 Hyungjin Chung, Suhyeon Lee, Jong Chul Ye

Moreover, our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.

MRI Reconstruction

Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model

no code implementations27 Feb 2023 Jaeyoung Huh, Sangjoon Park, Jeong Eun Lee, Jong Chul Ye

Automatic Speech Recognition (ASR) is a technology that converts spoken words into text, facilitating interaction between humans and machines.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models

no code implementations8 Feb 2023 Hyeonho Jeong, Gihyun Kwon, Jong Chul Ye

Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language.

Language Modelling Large Language Model

Don't Play Favorites: Minority Guidance for Diffusion Models

no code implementations29 Jan 2023 Soobin Um, Jong Chul Ye

The minority samples are instances that lie on low-density regions of a data manifold.

ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts

no code implementations28 Jan 2023 Kwanyoung Kim, Yujin Oh, Jong Chul Ye

In particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed to learn an optimal mapping between multiple text prompts and visual feature maps of the frozen image encoder hidden layers.

Semantic Segmentation Zero Shot Segmentation +1

Minimizing Trajectory Curvature of ODE-based Generative Models

1 code implementation27 Jan 2023 Sangyun Lee, Beomsu Kim, Jong Chul Ye

Based on the relationship between the forward process and the curvature, here we present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.

Annealed Score-Based Diffusion Model for MR Motion Artifact Reduction

no code implementations8 Jan 2023 Gyutaek Oh, Jeong Eun Lee, Jong Chul Ye

Motion artifact reduction is one of the important research topics in MR imaging, as the motion artifact degrades image quality and makes diagnosis difficult.

Single-round Self-supervised Distributed Learning using Vision Transformer

no code implementations5 Jan 2023 Sangjoon Park, Ik-Jae Lee, Jun Won Kim, Jong Chul Ye

Despite the recent success of deep learning in the field of medicine, the issue of data scarcity is exacerbated by concerns about privacy and data ownership.

Federated Learning

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

no code implementations CVPR 2023 Hyungjin Chung, Dohoon Ryu, Michael T. McCann, Marc L. Klasky, Jong Chul Ye

Diffusion models have emerged as the new state-of-the-art generative model with high quality samples, with intriguing properties such as mode coverage and high flexibility.

Image Reconstruction

Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model

1 code implementation19 Nov 2022 Jinho Chang, Jong Chul Ye

The recent success of large foundation models in artificial intelligence has prompted the emergence of chemical pre-trained models.

Molecular Property Prediction Property Prediction

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

no code implementations CVPR 2023 Hyungjin Chung, Jeongsol Kim, Sehui Kim, Jong Chul Ye

We show the efficacy of our method on two representative tasks -- blind deblurring, and imaging through turbulence -- and show that our method yields state-of-the-art performance, while also being flexible to be applicable to general blind inverse problems when we know the functional forms.


Training Debiased Subnetworks with Contrastive Weight Pruning

1 code implementation CVPR 2023 Geon Yeong Park, Sangmin Lee, Sang Wan Lee, Jong Chul Ye

Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize.

Facial Attribute Classification

Self-supervised debiasing using low rank regularization

no code implementations11 Oct 2022 Geon Yeong Park, Chanyong Jung, Jong Chul Ye, Sang Wan Lee

We first pretrain a biased encoder in a self-supervised manner with the rank regularization, serving as a semantic bottleneck to enforce the encoder to learn the spuriously correlated attributes.

Self-Supervised Learning

Diffusion-based Image Translation using Disentangled Style and Content Representation

1 code implementation30 Sep 2022 Gihyun Kwon, Jong Chul Ye

Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains.

Style Transfer Translation

Diffusion Posterior Sampling for General Noisy Inverse Problems

1 code implementation29 Sep 2022 Hyungjin Chung, Jeongsol Kim, Michael T. McCann, Marc L. Klasky, Jong Chul Ye

Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers.

Deblurring Retrieval

Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation

no code implementations29 Sep 2022 Boah Kim, Yujin Oh, Jong Chul Ye

Also, by adversarial learning based on the proposed switchable spatially-adaptive denormalization, our model estimates synthetic fake vessel images as well as vessel segmentation masks, which further makes the model capture vessel-relevant semantic information.

Denoising Representation Learning

Denoising MCMC for Accelerating Diffusion-Based Generative Models

1 code implementation29 Sep 2022 Beomsu Kim, Jong Chul Ye

Diffusion models are powerful generative models that simulate the reverse of diffusion processes using score functions to synthesize data from noise.

Denoising Image Generation

Magnitude and Angle Dynamics in Training Single ReLU Neurons

no code implementations27 Sep 2022 Sangmin Lee, Byeongsu Sim, Jong Chul Ye

To understand learning the dynamics of deep ReLU networks, we investigate the dynamic system of gradient flow $w(t)$ by decomposing it to magnitude $w(t)$ and angle $\phi(t):= \pi - \theta(t) $ components.

Self-supervised Multi-modal Training from Uncurated Image and Reports Enables Zero-shot Oversight Artificial Intelligence in Radiology

1 code implementation10 Aug 2022 Sangjoon Park, Eun Sun Lee, Kyung Sook Shin, Jeong Eun Lee, Jong Chul Ye

Recent advances in vision-language models sheds a light on the long-standing problems of the oversight AI by the understanding both visual and textual concepts and their semantic correspondences.

Contrastive Learning Decision Making +3

Pyramidal Denoising Diffusion Probabilistic Models

no code implementations3 Aug 2022 Dohoon Ryu, Jong Chul Ye

Recently, diffusion model have demonstrated impressive image generation performances, and have been extensively studied in various computer vision tasks.

Denoising Image Generation +1

Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis

1 code implementation16 Jul 2022 Sangyun Lee, Hyungjin Chung, Jaehyeon Kim, Jong Chul Ye

We further propose a blur diffusion as a special case, where each frequency component of an image is diffused at different speeds.

Deblurring Image Generation +1

Patch-wise Deep Metric Learning for Unsupervised Low-Dose CT Denoising

1 code implementation6 Jul 2022 Chanyong Jung, Joonhyung Lee, Sunkyoung You, Jong Chul Ye

The acquisition conditions for low-dose and high-dose CT images are usually different, so that the shifts in the CT numbers often occur.

Denoising Metric Learning

Diffusion Deformable Model for 4D Temporal Medical Image Generation

1 code implementation27 Jun 2022 Boah Kim, Jong Chul Ye

Our proposed DDM is composed of the diffusion and the deformation modules so that DDM can learn spatial deformation information between the source and target volumes and provide a latent code for generating intermediate frames along a geodesic path.

Denoising Image Generation +1

Improving Diffusion Models for Inverse Problems using Manifold Constraints

2 code implementations2 Jun 2022 Hyungjin Chung, Byeongsu Sim, Dohoon Ryu, Jong Chul Ye

Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process.

Colorization Image Inpainting

Mitigating Out-of-Distribution Data Density Overestimation in Energy-Based Models

no code implementations30 May 2022 Beomsu Kim, Jong Chul Ye

Deep energy-based models (EBMs), which use deep neural networks (DNNs) as energy functions, are receiving increasing attention due to their ability to learn complex distributions.

Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutation

no code implementations7 Apr 2022 Sangjoon Park, Jong Chul Ye

The widespread application of artificial intelligence in health research is currently hampered by limitations in data availability.

Federated Learning Management +1

MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion

no code implementations23 Mar 2022 Hyungjin Chung, Eun Sun Lee, Jong Chul Ye

Our network, trained only with coronal knee scans, excels even on out-of-distribution in vivo liver MRI data, contaminated with complex mixture of noise.

Image Denoising Super-Resolution

One-Shot Adaptation of GAN in Just One CLIP

3 code implementations17 Mar 2022 Gihyun Kwon, Jong Chul Ye

Specifically, our model employs a two-step training strategy: reference image search in the source generator using a CLIP-guided latent optimization, followed by generator fine-tuning with a novel loss function that imposes CLIP space consistency between the source and adapted generators.

Image Retrieval

Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks

1 code implementation CVPR 2022 Chanyong Jung, Gihyun Kwon, Jong Chul Ye

Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence.

Contrastive Learning Image-to-Image Translation +1

Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment

no code implementations17 Feb 2022 Yujin Oh, Go Eun Bae, Kyung-Hee Kim, Min-Kyung Yeo, Jong Chul Ye

Our results demonstrate that AI-assisted gastric endoscopic screening has a great potential for providing presumptive pathologic opinion and appropriate cancer treatment of gastric cancer in practical clinical settings.

whole slide images

Phase Aberration Robust Beamformer for Planewave US Using Self-Supervised Learning

no code implementations16 Feb 2022 Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

Ultrasound (US) is widely used for clinical imaging applications thanks to its real-time and non-invasive nature.

Self-Supervised Learning

AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation

no code implementations13 Feb 2022 Sangjoon Park, Gwanghyun Kim, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Chang Min Park, Jong Chul Ye

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust deep learning model requires large, high-quality data with manual annotation, which is expensive to obtain.

Knowledge Distillation Self-Supervised Learning

Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks

no code implementations11 Feb 2022 Sangmin Lee, Byeongsu Sim, Jong Chul Ye

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research.

Energy-Based Contrastive Learning of Visual Representations

1 code implementation10 Feb 2022 Beomsu Kim, Jong Chul Ye

Contrastive learning is a method of learning visual representations by training Deep Neural Networks (DNNs) to increase the similarity between representations of positive pairs (transformations of the same image) and reduce the similarity between representations of negative pairs (transformations of different images).

Contrastive Learning Self-Supervised Learning

DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model

no code implementations9 Dec 2021 Boah Kim, Inhwa Han, Jong Chul Ye

Specifically, the deformation fields are generated by the conditional score function of the deformation between the moving and fixed images, so that the registration can be performed from continuous deformation by simply scaling the latent feature of the score.

Image Registration Medical Image Registration

Tunable Image Quality Control of 3-D Ultrasound using Switchable CycleGAN

no code implementations6 Dec 2021 Jaeyoung Huh, Shujaat Khan, Sungjin Choi, Dongkuk Shin, Eun Sun Lee, Jong Chul Ye

In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US imaging system can visualize a volume along three axial planes.

Anatomy Image Enhancement

Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching

no code implementations CVPR 2022 Kwanyoung Kim, Taesung Kwon, Jong Chul Ye

Through extensive experiments, we demonstrate that the proposed method can accurately estimate noise models and parameters, and provide the state-of-the-art self-supervised image denoising performance in the benchmark dataset and real-world dataset.

Image Denoising

CLIPstyler: Image Style Transfer with a Single Text Condition

3 code implementations CVPR 2022 Gihyun Kwon, Jong Chul Ye

In order to deal with such applications, we propose a new framework that enables a style transfer `without' a style image, but only with a text description of the desired style.

Style Transfer

Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images

no code implementations NeurIPS 2021 Kwanyoung Kim, Jong Chul Ye

Recently, there has been extensive research interest in training deep networks to denoise images without clean reference. However, the representative approaches such as Noise2Noise, Noise2Void, Stein's unbiased risk estimator (SURE), etc.

Image Denoising

Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis

no code implementations NeurIPS 2021 Sangjoon Park, Gwanghyun Kim, Jeongsol Kim, Boah Kim, Jong Chul Ye

For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals.

COVID-19 Diagnosis Federated Learning

Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training

no code implementations2 Nov 2021 Sangjoon Park, Gwanghyun Kim, Jeongsol Kim, Boah Kim, Jong Chul Ye

For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals.

COVID-19 Diagnosis Federated Learning

Performance Analysis of Fractional Learning Algorithms

no code implementations11 Oct 2021 Abdul Wahab, Shujaat Khan, Imran Naseem, Jong Chul Ye

Fractional learning algorithms are trending in signal processing and adaptive filtering recently.

Score-based diffusion models for accelerated MRI

1 code implementation8 Oct 2021 Hyungjin Chung, Jong Chul Ye

Leveraging the learned score function as a prior, here we introduce a way to sample data from a conditional distribution given the measurements, such that the model can be readily used for solving inverse problems in imaging, especially for accelerated MRI.


DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation

1 code implementation CVPR 2022 Gwanghyun Kim, Taesung Kwon, Jong Chul Ye

To mitigate these problems and enable faithful manipulation of real images, we propose a novel method, dubbed DiffusionCLIP, that performs text-driven image manipulation using diffusion models.

Image Generation Image Manipulation +1

Privacy-preserving Task-Agnostic Vision Transformer for Image Processing

1 code implementation29 Sep 2021 Boah Kim, Jeongsol Kim, Jong Chul Ye

Inspired by the recent success of Vision Transformer (ViT), here we present a new distributed learning framework for image processing applications, allowing clients to learn multiple tasks with their private data.

Multi-Task Learning Privacy Preserving

Federated Contrastive Learning for Privacy-Preserving Unpaired Image-to-Image Translation

no code implementations29 Sep 2021 Joonyoung Song, Jong Chul Ye

In addition, by combining it with the pre-trained VGG network, the learnable part of the discriminator can be further reduced without impairing the image quality, resulting in two order magnitude reduction in the communication cost.

Contrastive Learning Privacy Preserving +2

Deep Learning for Ultrasound Beamforming

no code implementations23 Sep 2021 Ruud JG van Sloun, Jong Chul Ye, Yonina C Eldar

Diagnostic imaging plays a critical role in healthcare, serving as a fundamental asset for timely diagnosis, disease staging and management as well as for treatment choice, planning, guidance, and follow-up.

Image Reconstruction Management

Federated CycleGAN for Privacy-Preserving Image-to-Image Translation

no code implementations17 Jun 2021 Joonyoung Song, Jong Chul Ye

Although the recent federated learning (FL) allows a neural network to be trained without data exchange, the basic assumption of the FL is that all clients have their own training data from a similar domain, which is different from our image-to-image translation scenario in which each client has images from its unique domain and the goal is to learn image translation between different domains without accessing the target domain data.

Federated Learning Privacy Preserving +2

Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images

no code implementations13 Jun 2021 Kwanyoung Kim, Jong Chul Ye

Recently, there has been extensive research interest in training deep networks to denoise images without clean reference.

Image Denoising

Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention

1 code implementation NeurIPS 2021 Byung-Hoon Kim, Jong Chul Ye, Jae-Jin Kim

Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention.

Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis

no code implementations NeurIPS 2021 Sangjoon Park, Gwanghyun Kim, Jeongsol Kim, Boah Kim, Jong Chul Ye

For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals.

COVID-19 Diagnosis Federated Learning

Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement

no code implementations17 May 2021 Mehmet Akçakaya, Burhaneddin Yaman, Hyungjin Chung, Jong Chul Ye

Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times.

Image Reconstruction Self-Supervised Learning

Simultaneous super-resolution and motion artifact removal in diffusion-weighted MRI using unsupervised deep learning

no code implementations1 May 2021 Hyungjin Chung, Jaehyun Kim, Jeong Hee Yoon, Jeong Min Lee, Jong Chul Ye

To the best of our knowledge, the proposed method is the first to tackle super-resolution and motion artifact correction simultaneously in the context of MRI using unsupervised learning.


Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN

no code implementations1 May 2021 Hyungjin Chung, Jong Chul Ye

Hence, we combine sliceGAN with AdaIN to endow the model with the ability to disentangle the features and control the synthesis.


Deep learning enables reference-free isotropic super-resolution for volumetric fluorescence microscopy

no code implementations19 Apr 2021 Hyoungjun Park, Myeongsu Na, Bumju Kim, Soohyun Park, Ki Hean Kim, Sunghoe Chang, Jong Chul Ye

Volumetric imaging by fluorescence microscopy is often limited by anisotropic spatial resolution from inferior axial resolution compared to the lateral resolution.


Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising

no code implementations17 Apr 2021 Taesung Kwon, Jong Chul Ye

Recently, CycleGAN was shown to provide high-performance, ultra-fast denoising for low-dose X-ray computed tomography (CT) without the need for a paired training dataset.

Computed Tomography (CT) Denoising

Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification

no code implementations15 Apr 2021 Sangjoon Park, Gwanghyun Kim, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Jong Chul Ye

This situation is ideally suited for the Vision Transformer (ViT) architecture, where a lot of unlabeled data can be used through structural modeling by the self-attention mechanism.

COVID-19 Diagnosis

CXR Segmentation by AdaIN-based Domain Adaptation and Knowledge Distillation

1 code implementation13 Apr 2021 Yujin Oh, Jong Chul Ye

As segmentation labels are scarce, extensive researches have been conducted to train segmentation networks with domain adaptation, semi-supervised or self-supervised learning techniques to utilize abundant unlabeled dataset.

Domain Adaptation Knowledge Distillation +1

PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing

1 code implementation7 Apr 2021 Byung-Hoon Kim, Joonyoung Song, Jong Chul Ye, JaeHyun Baek

Reconstructing RGB image from RAW data obtained with a mobile device is related to a number of image signal processing (ISP) tasks, such as demosaicing, denoising, etc.

Demosaicking Denoising

Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation

1 code implementation ICCV 2021 Gihyun Kwon, Jong Chul Ye

One of the important research topics in image generative models is to disentangle the spatial contents and styles for their separate control.

Disentanglement Image Generation +1

Missing Cone Artifacts Removal in ODT using Unsupervised Deep Learning in Projection Domain

no code implementations16 Mar 2021 Hyungjin Chung, Jaeyoung Huh, Geon Kim, Yong Keun Park, Jong Chul Ye

Optical diffraction tomography (ODT) produces three dimensional distribution of refractive index (RI) by measuring scattering fields at various angles.

Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus

no code implementations12 Mar 2021 Sangjoon Park, Gwanghyun Kim, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Jong Chul Ye

Under the global COVID-19 crisis, developing robust diagnosis algorithm for COVID-19 using CXR is hampered by the lack of the well-curated COVID-19 data set, although CXR data with other disease are abundant.

Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer

no code implementations12 Mar 2021 Gwanghyun Kim, Sangjoon Park, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Jong Chul Ye

Under the global pandemic of COVID-19, building an automated framework that quantifies the severity of COVID-19 and localizes the relevant lesion on chest X-ray images has become increasingly important.

Lesion Segmentation

CycleQSM: Unsupervised QSM Deep Learning using Physics-Informed CycleGAN

no code implementations7 Dec 2020 Gyutaek Oh, Hyokyoung Bae, Hyun-Seo Ahn, Sung-Hong Park, Jong Chul Ye

In contrast to the conventional cycleGAN, our novel cycleGAN has only one generator and one discriminator thanks to the known dipole kernel.

Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN

2 code implementations26 Nov 2020 Serin Yang, Eung Yeop Kim, Jong Chul Ye

We also show that the quality of generated images can be further improved if intermediate kernel domain images are available.

Computed Tomography (CT)

DeepPhaseCut: Deep Relaxation in Phase for Unsupervised Fourier Phase Retrieval

no code implementations20 Nov 2020 Eunju Cha, Chanseok Lee, Mooseok Jang, Jong Chul Ye

Unlike the existing deep learning approaches that use a neural network as a regularization term or an end-to-end blackbox model for supervised training, our algorithm is a feed-forward neural network implementation of PhaseCut algorithm in an unsupervised learning framework.

Image Reconstruction Retrieval

Unsupervised MR Motion Artifact Deep Learning using Outlier-Rejecting Bootstrap Aggregation

no code implementations12 Nov 2020 Gyutaek Oh, Jeong Eun Lee, Jong Chul Ye

Recently, deep learning approaches for MR motion artifact correction have been extensively studied.

Switchable Deep Beamformer

no code implementations31 Aug 2020 Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

Recent proposals of deep beamformers using deep neural networks have attracted significant attention as computational efficient alternatives to adaptive and compressive beamformers.

Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN

no code implementations29 Aug 2020 Gyutaek Oh, Byeongsu Sim, Hyungjin Chung, Leonard Sunwoo, Jong Chul Ye

Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced runtime complexity.

CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration

no code implementations13 Aug 2020 Boah Kim, Dong Hwan Kim, Seong Ho Park, Jieun Kim, June-Goo Lee, Jong Chul Ye

However, the existing deep learning methods still have limitation in the preservation of original topology during the deformation with registration vector fields.

Image Registration

AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising

no code implementations13 Aug 2020 Jawook Gu, Jong Chul Ye

The secondary auxiliary generator is needed to enforce the cycle-consistency, but the additional memory requirement and increases of the learnable parameters are the main huddles for cycleGAN training.


Two-Stage Deep Learning for Accelerated 3D Time-of-Flight MRA without Matched Training Data

no code implementations4 Aug 2020 Hyungjin Chung, Eunju Cha, Leonard Sunwoo, Jong Chul Ye

Time-of-flight magnetic resonance angiography (TOF-MRA) is one of the most widely used non-contrast MR imaging methods to visualize blood vessels, but due to the 3-D volume acquisition highly accelerated acquisition is necessary.

Image Reconstruction

OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN

no code implementations10 Jul 2020 Jaeyoung Huh, Shujaat Khan, Jong Chul Ye

Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type.

Pushing the Limit of Unsupervised Learning for Ultrasound Image Artifact Removal

no code implementations26 Jun 2020 Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

Experimental results for various tasks such as deconvolution, speckle removal, limited data artifact removal, etc.

Deep Learning COVID-19 Features on CXR using Limited Training Data Sets

2 code implementations13 Apr 2020 Yujin Oh, Sangjoon Park, Jong Chul Ye

Under the global pandemic of COVID-19, the use of artificial intelligence to analyze chest X-ray (CXR) image for COVID-19 diagnosis and patient triage is becoming important.

COVID-19 Diagnosis

Unsupervised Deep Learning for MR Angiography with Flexible Temporal Resolution

no code implementations29 Mar 2020 Eunju Cha, Hyungjin Chung, Eung Yeop Kim, Jong Chul Ye

This is because high spatio-temporal resolution ground-truth images are not available for tMRA.

Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction

no code implementations17 Mar 2020 Eunju Cha, Gyutaek Oh, Jong Chul Ye

Recently, it was shown that an encoder-decoder convolutional neural network (CNN) can be interpreted as a piecewise linear basis-like representation, whose specific representation is determined by the ReLU activation patterns for a given input image.

Unsupervised Denoising for Satellite Imagery using Wavelet Subband CycleGAN

no code implementations23 Feb 2020 Joonyoung Song, Jae-Heon Jeong, Dae-Soon Park, Hyun-Ho Kim, Doo-Chun Seo, Jong Chul Ye

Recently, deep learning approaches have been extensively explored for the removal of noises in satellite imagery.


Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis

1 code implementation10 Jan 2020 Byung-Hoon Kim, Jong Chul Ye

This understanding enables us to exploit CNN-based saliency map techniques for the GNN, which we tailor to the proposed GIN with one-hot encoding, to visualize the important regions of the brain.

General Classification Graph Classification

Structured Low-Rank Algorithms: Theory, MR Applications, and Links to Machine Learning

1 code implementation27 Oct 2019 Mathews Jacob, Merry P. Mani, Jong Chul Ye

In this survey, we provide a detailed review of recent advances in the recovery of continuous domain multidimensional signals from their few non-uniform (multichannel) measurements using structured low-rank matrix completion formulation.

BIG-bench Machine Learning Low-Rank Matrix Completion


no code implementations25 Sep 2019 Eunju Cha, Jaeduck Jang, Junho Lee, Eunha Lee, Jong Chul Ye

However, the computation of the divergence term in SURE is difficult to implement in a neural network framework, and the condition to avoid trivial identity mapping is not well defined.


Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems

no code implementations25 Sep 2019 Byeongsu Sim, Gyutaek Oh, Jeongsol Kim, Chanyong Jung, Jong Chul Ye

To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1 distance.

Computed Tomography (CT) Super-Resolution

CycleGAN with a Blur Kernel for Deconvolution Microscopy: Optimal Transport Geometry

no code implementations26 Aug 2019 Sungjun Lim, Hyoungjun Park, Sang-Eun Lee, Sunghoe Chang, Jong Chul Ye

Deconvolution microscopy has been extensively used to improve the resolution of the wide-field fluorescent microscopy, but the performance of classical approaches critically depends on the accuracy of a model and optimization algorithms.

Image Deconvolution

Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound

no code implementations24 Jul 2019 Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

In ultrasound (US) imaging, various types of adaptive beamforming techniques have been investigated to improve the resolution and contrast-to-noise ratio of the delay and sum (DAS) beamformers.

Boosting CNN beyond Label in Inverse Problems

no code implementations18 Jun 2019 Eunju Cha, Jaeduck Jang, Junho Lee, Eunha Lee, Jong Chul Ye

In this paper, we show that the recent unsupervised learning methods such as Noise2Noise, Stein's unbiased risk estimator (SURE)-based denoiser, and Noise2Void are closely related to each other in their formulation of an unbiased estimator of the prediction error, but each of them are associated with its own limitations.

Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal

no code implementations17 Jun 2019 Yoseob Han, Junyoung Kim, Jong Chul Ye

Conebeam CT using a circular trajectory is quite often used for various applications due to its relative simple geometry.

Which Contrast Does Matter? Towards a Deep Understanding of MR Contrast using Collaborative GAN

2 code implementations10 May 2019 Dongwook Lee, Won-Jin Moon, Jong Chul Ye

Thanks to the recent success of generative adversarial network (GAN) for image synthesis, there are many exciting GAN approaches that successfully synthesize MR image contrast from other images with different contrasts.

Image Generation Image Imputation +2

Mumford-Shah Loss Functional for Image Segmentation with Deep Learning

2 code implementations5 Apr 2019 Boah Kim, Jong Chul Ye

This loss function is based on the observation that the softmax layer of deep neural networks has striking similarity to the characteristic function in the Mumford-Shah functional.

Image Segmentation Unsupervised Semantic Segmentation

Deep Learning-based Universal Beamformer for Ultrasound Imaging

no code implementations5 Apr 2019 Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

In ultrasound (US) imaging, individual channel RF measurements are back-propagated and accumulated to form an image after applying specific delays.

Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer

no code implementations5 Apr 2019 Sungjun Lim, Sang-Eun Lee, Sunghoe Chang, Jong Chul Ye

In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm.

Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning

no code implementations4 Apr 2019 Saiprasad Ravishankar, Jong Chul Ye, Jeffrey A. Fessler

This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.

BIG-bench Machine Learning Computed Tomography (CT) +1

CollaGAN : Collaborative GAN for Missing Image Data Imputation

1 code implementation28 Jan 2019 Dongwook Lee, Junyoung Kim, Won-Jin Moon, Jong Chul Ye

In many applications requiring multiple inputs to obtain a desired output, if any of the input data is missing, it often introduces large amounts of bias.

Image Imputation Imputation +1

Understanding Geometry of Encoder-Decoder CNNs

no code implementations22 Jan 2019 Jong Chul Ye, Woon Kyoung Sung

Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems.

Universal Deep Beamformer for Variable Rate Ultrasound Imaging

1 code implementation7 Jan 2019 Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

In particular, we design an end-to-end deep learning framework that can directly process sub-sampled RF data acquired at different subsampling rate and detector configuration to generate high quality ultrasound images using a single beamformer.

One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection

1 code implementation1 Oct 2018 Yoseob Han, Jong Chul Ye

The first type learns ROI size-specific cupping artifacts from the analytic reconstruction images, whereas the second type network is to learn to invert the finite Hilbert transform from the truncated differentiated backprojection (DBP) data.

Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography

1 code implementation26 Jun 2018 Eunhee Kang, Hyun Jung Koo, Dong Hyun Yang, Joon Bum Seo, Jong Chul Ye

Although this reduces the total radiation dose, the image quality during the low-dose phases is significantly degraded.


k-Space Deep Learning for Parallel MRI: Application to Time-Resolved MR Angiography

no code implementations3 Jun 2018 Eunju Cha, Eung Yeop Kim, Jong Chul Ye

Time-resolved angiography with interleaved stochastic trajectories (TWIST) has been widely used for dynamic contrast enhanced MRI (DCE-MRI).

k-Space Deep Learning for Reference-free EPI Ghost Correction

no code implementations1 Jun 2018 Juyoung Lee, Yoseob Han, Jae-Kyun Ryu, Jang-Yeon Park, Jong Chul Ye

Reconstruction results using 3T and 7T in-vivo data showed that the proposed method outperformed the image quality compared to the existing methods, and the computing time is much faster. The proposed k-space deep learning for EPI ghost correction is highly robust and fast, and can be combined with acceleration, so that it can be used as a promising correction tool for high-field MRI without changing the current acquisition protocol.

Matrix Completion

k-Space Deep Learning for Accelerated MRI

1 code implementation10 May 2018 Yoseob Han, Leonard Sunwoo, Jong Chul Ye

The annihilating filter-based low-rank Hankel matrix approach (ALOHA) is one of the state-of-the-art compressed sensing approaches that directly interpolates the missing k-space data using low-rank Hankel matrix completion.

Denoising Matrix Completion

Quantitative Susceptibility Map Reconstruction Using Annihilating Filter-based Low-Rank Hankel Matrix Approach

no code implementations25 Apr 2018 Hyun-Seo Ahn, Sung-Hong Park, Jong Chul Ye

Quantitative susceptibility mapping (QSM) inevitably suffers from streaking artifacts caused by zeros on the conical surface of the dipole kernel in k-space.

Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networks

no code implementations2 Apr 2018 Dongwook Lee, Jaejun Yoo, Sungho Tak, Jong Chul Ye

The proposed deep residual learning networks are composed of magnitude and phase networks that are separately trained.

Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner

no code implementations4 Jan 2018 Yoseob Han, Jingu Kang, Jong Chul Ye

For homeland and transportation security applications, 2D X-ray explosive detection system (EDS) have been widely used, but they have limitations in recognizing 3D shape of the hidden objects.

3D Reconstruction Computed Tomography (CT)

Deep Learning Interior Tomography for Region-of-Interest Reconstruction

no code implementations29 Dec 2017 Yoseob Han, Jawook Gu, Jong Chul Ye

Interior tomography for the region-of-interest (ROI) imaging has advantages of using a small detector and reducing X-ray radiation dose.

Efficient B-mode Ultrasound Image Reconstruction from Sub-sampled RF Data using Deep Learning

1 code implementation17 Dec 2017 Yeo Hun Yoon, Shujaat Khan, Jaeyoung Huh, Jong Chul Ye

In portable, three dimensional, and ultra-fast ultrasound imaging systems, there is an increasing demand for the reconstruction of high quality images from a limited number of radio-frequency (RF) measurements due to receiver (Rx) or transmit (Xmit) event sub-sampling.

Image Reconstruction

Deep Learning Diffuse Optical Tomography

no code implementations4 Dec 2017 Jaejun Yoo, Sohail Sabir, Duchang Heo, Kee Hyun Kim, Abdul Wahab, Yoonseok Choi, Seul-I Lee, Eun Young Chae, Hak Hee Kim, Young Min Bae, Young-wook Choi, Seungryong Cho, Jong Chul Ye

Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level.

Breast Cancer Detection

Deep Learning for Accelerated Ultrasound Imaging

no code implementations27 Oct 2017 Yeo Hun Yoon, Jong Chul Ye

In portable, 3-D, or ultra-fast ultrasound (US) imaging systems, there is an increasing demand to reconstruct high quality images from limited number of data.

Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT

3 code implementations28 Aug 2017 Yoseob Han, Jong Chul Ye

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose.

Computed Tomography (CT)

Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network

1 code implementation31 Jul 2017 Eunhee Kang, Jaejun Yoo, Jong Chul Ye

To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge.


Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems

4 code implementations3 Jul 2017 Jong Chul Ye, Yoseob Han, Eunju Cha

Using numerical experiments with various inverse problems, we demonstrated that our deep convolution framelets network shows consistent improvement over existing deep architectures. This discovery suggests that the success of deep learning is not from a magical power of a black-box, but rather comes from the power of a novel signal representation using non-local basis combined with data-driven local basis, which is indeed a natural extension of classical signal processing theory.

Geometric GAN

6 code implementations8 May 2017 Jae Hyun Lim, Jong Chul Ye

Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other.

Text Generation

Wavelet Domain Residual Network (WavResNet) for Low-Dose X-ray CT Reconstruction

2 code implementations4 Mar 2017 Eunhee Kang, Junhong Min, Jong Chul Ye

Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally complex because of the repeated use of the forward and backward projection.

Low-Dose X-Ray Ct Reconstruction

Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction

no code implementations4 Mar 2017 Jawook Gu, Jong Chul Ye

Limited-angle computed tomography (CT) is often used in clinical applications such as C-arm CT for interventional imaging.

Computed Tomography (CT)

Deep artifact learning for compressed sensing and parallel MRI

no code implementations3 Mar 2017 Dongwook Lee, Jaejun Yoo, Jong Chul Ye

Furthermore, the computational time is by order of magnitude faster.

Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MR

1 code implementation3 Mar 2017 Yo Seob Han, Jaejun Yoo, Jong Chul Ye

To address the situation given the limited available data, we propose a domain adaptation scheme that employs a pre-trained network using a large number of x-ray computed tomography (CT) or synthesized radial MR datasets, which is then fine-tuned with only a few radial MR datasets.

Computed Tomography (CT) Domain Adaptation

Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis

no code implementations19 Nov 2016 Yo Seob Han, Jaejun Yoo, Jong Chul Ye

Recently, compressed sensing (CS) computed tomography (CT) using sparse projection views has been extensively investigated to reduce the potential risk of radiation to patient.

Computed Tomography (CT) Image Reconstruction

Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification

1 code implementation19 Nov 2016 Woong Bae, Jaejun Yoo, Jong Chul Ye

To address this issue, here we propose a novel feature space deep residual learning algorithm that outperforms the existing residual learning.

Color Image Denoising Image Restoration +1

A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction

no code implementations31 Oct 2016 Eunhee Kang, Junhong Min, Jong Chul Ye

To the best of our knowledge, this work is the first deep learning architecture for low-dose CT reconstruction that has been rigorously evaluated and proven for its efficacy.

Denoising Low-Dose X-Ray Ct Reconstruction

Sparse + Low Rank Decomposition of Annihilating Filter-based Hankel Matrix for Impulse Noise Removal

1 code implementation19 Oct 2015 Kyong Hwan Jin, Jong Chul Ye

The new approach, what we call the robust ALOHA, is motivated by the observation that an image corrupted with impulse noises has intact pixels; so the impulse noises can be modeled as sparse components, whereas the underlying image can be still modeled using a low-rank Hankel structured matrix.

Image Inpainting

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