1 code implementation • 16 Oct 2024 • Jiye Kim, Minjun Kim, Sooyeon Ji, Kyeongseon Min, Hwihun Jeong, Hyeong-Geol Shin, Chungseok Oh, Sina Straub, Seong-Gi Kim, Jongho Lee
The proposed method is compared with alternative pipelines, such as an end-to-end network and linearly-scaled $R_2'$, and is validated against $\chi$-separation maps at 3T, demonstrating its accuracy.
no code implementations • 21 Sep 2024 • Minjun Kim, Sooyeon Ji, Jiye Kim, Kyeongseon Min, Hwihun Jeong, Jonghyo Youn, Taechang Kim, Jinhee Jang, Berkin Bilgic, Hyeong-Geol Shin, Jongho Lee
Magnetic susceptibility source separation ($\chi$-separation), an advanced quantitative susceptibility mapping (QSM) method, enables the separate estimation of para- and diamagnetic susceptibility source distributions in the brain.
no code implementations • 18 Sep 2024 • Seongmin Hong, Jaehyeok Bae, Jongho Lee, Se Young Chun
Our method outperforms joint optimization of sampling-reconstruction ($\mathcal{H}_1$) and adaptive sampling ($\mathcal{H}_2$) by achieving significant improvements on several Fourier CS problems.
1 code implementation • 16 Sep 2024 • Hwihun Jeong, Se Young Chun, Jongho Lee
To mitigate this issue, downstream task-oriented reconstruction optimization has been proposed for a single downstream task.
1 code implementation • 22 Apr 2024 • Adrian de Wynter, Ishaan Watts, Nektar Ege Altıntoprak, Tua Wongsangaroonsri, Minghui Zhang, Noura Farra, Lena Baur, Samantha Claudet, Pavel Gajdusek, Can Gören, Qilong Gu, Anna Kaminska, Tomasz Kaminski, Ruby Kuo, Akiko Kyuba, Jongho Lee, Kartik Mathur, Petter Merok, Ivana Milovanović, Nani Paananen, Vesa-Matti Paananen, Anna Pavlenko, Bruno Pereira Vidal, Luciano Strika, Yueh Tsao, Davide Turcato, Oleksandr Vakhno, Judit Velcsov, Anna Vickers, Stéphanie Visser, Herdyan Widarmanto, Andrey Zaikin, Si-Qing Chen
Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern.
no code implementations • 7 Apr 2024 • Vlad Fomenko, Han Yu, Jongho Lee, Stanley Hsieh, Weizhu Chen
LoRA (Low-Rank Adaptation) has emerged as a preferred method for efficiently adapting Large Language Models (LLMs) with remarkable simplicity and efficacy.
1 code implementation • 15 Feb 2024 • Taesu Kim, Jongho Lee, Daehyun Ahn, Sarang Kim, Jiwoong Choi, Minkyu Kim, HyungJun Kim
We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs).
no code implementations • 4 Dec 2023 • Heejun Shin, Taehee Kim, Jongho Lee, Se Young Chun, Seungryung Cho, Dongmyung Shin
In the FACT method, we meta-trained a neural network and a hash-encoder using a few scans (= 15), and a new regularization technique is utilized to reconstruct the details of an anatomical structure.
no code implementations • 8 Nov 2023 • Kyeongseon Min, Beomseok Sohn, Woo Jung Kim, Chae Jung Park, Soohwa Song, Dong Hoon Shin, Kyung Won Chang, Na-Young Shin, Minjun Kim, Hyeong-Geol Shin, Phil Hyu Lee, Jongho Lee
Iron and myelin are primary susceptibility sources in the human brain.
1 code implementation • ICCV 2023 • Hwihun Jeong, Heejoon Byun, Dong Un Kang, Jongho Lee
These differences in images create a domain gap that needs to be bridged by a step called image harmonization, to process the images successfully using conventional or deep learning-based image analysis (e. g., segmentation).
no code implementations • 16 Aug 2022 • Juhyung Park, Dongwon Park, Hyeong-Geol Shin, Eun-Jung Choi, Hongjun An, Minjun Kim, Dongmyung Shin, Se Young Chun, Jongho Lee
Hence, methods such as Noise2Noise (N2N) that require only pairs of noise-corrupted images have been developed to reduce the burden of obtaining training datasets.
no code implementations • CVPR 2021 • Jongho Lee, Mohit Gupta
For several vision and robotics applications, 3D geometry of man-made environments such as indoor scenes can be represented with a small number of dominant planes.
1 code implementation • 7 May 2021 • Dongmyung Shin, Younghoon Kim, Chungseok Oh, Hongjun An, Juhyung Park, Jiye Kim, Jongho Lee
This work may lay the foundation for an emerging field of AI-driven RF waveform design.
1 code implementation • 4 Feb 2021 • Juhung Park, Woojin Jung, Eun-Jung Choi, Se-Hong Oh, Dongmyung Shin, Hongjun An, Jongho Lee
In this study, a new deep neural network, referred to as DIFFnet, is developed to function as a generalized reconstruction tool of the diffusion-weighted signals for various gradient schemes and b-values.
no code implementations • 19 Jul 2020 • Hongjun An, Hyeong-Geol Shin, Sooyoen Ji, Woojin Jung, SeHong Oh, Dongmyung Shin, Juhyung Park, Jongho Lee
DeepResp is designed to extract the respiration-induced phase errors from a complex image using deep neural networks.
Image and Video Processing
no code implementations • 1 Nov 2019 • Giulio Aielli, Eli Ben-Haim, Roberto Cardarelli, Matthew John Charles, Xabier Cid Vidal, Victor Coco, Biplab Dey, Raphael Dumps, Jared A. Evans, George Gibbons, Olivier Le Dortz, Vladimir V. Gligorov, Philip Ilten, Simon Knapen, Jongho Lee, Saul López Soliño, Benjamin Nachman, Michele Papucci, Francesco Polci, Robin Quessard, Harikrishnan Ramani, Dean J. Robinson, Heinrich Schindler, Michael D. Sokoloff, Paul Swallow, Riccardo Vari, Nigel Watson, Mike Williams
A design overview is presented for the CODEX-$\beta$ demonstrator detector, which will enable background calibration and detector design studies.
High Energy Physics - Experiment High Energy Physics - Phenomenology
no code implementations • ICCV 2019 • Jongho Lee, Mohit Gupta
As continuous-wave time-of-flight (C-ToF) cameras become popular in 3D imaging applications, they need to contend with the problem of multi-camera interference (MCI).
1 code implementation • 29 Apr 2019 • Jieun Lee, Doohee Lee, Joon Yul Choi, Dongmyung Shin, Hyeong-Geol Shin, Jongho Lee
Purpose: To demonstrate the application of artificial-neural-network (ANN) for real-time processing of myelin water imaging (MWI).
Image and Video Processing