83 citations · 756 across the 59 of their papers we have counts for
21 papers · 1 filter
Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
Jinho Chang, Jong Chul Ye
The recent success of large foundation models in artificial intelligence has prompted the emergence of chemical pre-trained models. Despite the growing interest in large molecular…
Magnitude and Angle Dynamics in Training Single ReLU Neurons
Sangmin Lee, Byeongsu Sim, Jong Chul Ye
To understand learning the dynamics of deep ReLU networks, we investigate the dynamic system of gradient flow by decomposing it to magnitude and angle $ϕ(t):= π- θ(t)…
Self-supervised debiasing using low rank regularization
Geon Yeong Park, Chanyong Jung, Sangmin Lee +2
Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. While most existing debiasing methods require full supervision on either sp…
Training Debiased Subnetworks with Contrastive Weight Pruning
Geon Yeong Park, Sangmin Lee, Sang Wan Lee +1
Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize. This raises an interesting question: ``Doe…
Pyramidal Denoising Diffusion Probabilistic Models
Dohoon Ryu, Jong Chul Ye
Recently, diffusion model have demonstrated impressive image generation performances, and have been extensively studied in various computer vision tasks. Unfortunately, training an…
Denoising MCMC for Accelerating Diffusion-Based Generative Models
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. The sampling process of diffus…
Diffusion-based Image Translation using Disentangled Style and Content Representation
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. Unfortunately,…
Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation
Boah Kim, Yujin Oh, Jong Chul Ye
Vessel segmentation in medical images is one of the important tasks in the diagnosis of vascular diseases and therapy planning. Although learning-based segmentation approaches have…
Self-supervised Multi-modal Training from Uncurated Image and Reports Enables Zero-shot Oversight Artificial Intelligence in Radiology
Sangjoon Park, Eun Sun Lee, Kyung Sook Shin +2
Oversight AI is an emerging concept in radiology where the AI forms a symbiosis with radiologists by continuously supporting radiologists in their decision-making. Recent advances…
Patch-wise Deep Metric Learning for Unsupervised Low-Dose CT Denoising
Chanyong Jung, Joonhyung Lee, Sunkyoung You +1
The acquisition conditions for low-dose and high-dose CT images are usually different, so that the shifts in the CT numbers often occur. Accordingly, unsupervised deep learning-bas…
Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
Sangyun Lee, Hyungjin Chung, Jaehyeon Kim +1
Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly…
Diffusion Deformable Model for 4D Temporal Medical Image Generation
Boah Kim, Jong Chul Ye
Temporal volume images with 3D+t (4D) information are often used in medical imaging to statistically analyze temporal dynamics or capture disease progression. Although deep-learnin…
Mitigating Out-of-Distribution Data Density Overestimation in Energy-Based Models
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
Sangjoon Park, Jong Chul Ye
The widespread application of artificial intelligence in health research is currently hampered by limitations in data availability. Distributed learning methods such as federated l…
MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion
Hyungjin Chung, Eun Sun Lee, Jong Chul Ye
Patient scans from MRI often suffer from noise, which hampers the diagnostic capability of such images. As a method to mitigate such artifact, denoising is largely studied both wit…
Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks
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. However, the m…
One-Shot Adaptation of GAN in Just One CLIP
Gihyun Kwon, Jong Chul Ye
There are many recent research efforts to fine-tune a pre-trained generator with a few target images to generate images of a novel domain. Unfortunately, these methods often suffer…
AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
Sangjoon Park, Gwanghyun Kim, Yujin Oh +7
Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust deep learning model requires large, high-quality…
Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment
Yujin Oh, Go Eun Bae, Kyung-Hee Kim +2
Gastric endoscopic screening is an effective way to decide appropriate gastric cancer (GC) treatment at an early stage, reducing GC-associated mortality rate. Although artificial i…
Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks
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. Unfortunately, eve…
Energy-Based Contrastive Learning of Visual Representations
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 (tr…