User profiles for Chiheon Kim

Chi Heon Kim

Seoul National University College of Medicine
Verified email at snu.ac.kr
Cited by 5213

Fast autoaugment

…, I Kim, T Kim, C Kim, S Kim - Advances in neural …, 2019 - proceedings.neurips.cc
Data augmentation is an essential technique for improving generalization ability of deep
learning models. Recently, AutoAugment\cite {cubuk2018autoaugment} has been proposed as …

Autoregressive image generation using residual quantization

D Lee, C Kim, S Kim, M Cho… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents
an image as a sequence of discrete codes. A short sequence length is important for an …

The efficacy of conventional radiofrequency denervation in patients with chronic low back pain originating from the facet joints: a meta-analysis of randomized …

CH Lee, CK Chung, CH Kim - The Spine Journal, 2017 - Elsevier
Background Context Radiofrequency denervation is commonly used for the treatment of
chronic facet joint pain that has been refractory to more conservative treatments, although the …

Efficacy and safety of full-endoscopic decompression via interlaminar approach for central or lateral recess spinal stenosis of the lumbar spine: a meta-analysis

CH Lee, M Choi, I Choi, CH Kim, HS Kim, MJ Sohn - Spine, 2018 - journals.lww.com
Study Design. A meta-analysis of five retrospective cohort studies. Objective. The aim of the
study was to delineate the efficacy and safety of full-endoscopic decompression via the …

Comparison of minimally invasive versus open transforaminal interbody lumbar fusion

CH Kim, K Easley, JS Lee, JY Hong… - Global spine …, 2020 - journals.sagepub.com
Study Design: Narrative review. Objectives: In this review, we address the question of whether
the literature supports the notion that minimally invasive transforaminal interbody fusion (…

Scalable neural architecture search for 3d medical image segmentation

S Kim, I Kim, S Lim, W Baek, C Kim, H Cho… - … Image Computing and …, 2019 - Springer
In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image
segmentation, to automatically optimize a neural architecture from a large design space. …

Generalizable implicit neural representations via instance pattern composers

C Kim, D Lee, S Kim, M Cho… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Despite recent advances in implicit neural representations (INRs), it remains challenging for
a coordinate-based multi-layer perceptron (MLP) of INRs to learn a common representation …

Stochastic block model for hypergraphs: Statistical limits and a semidefinite programming approach

C Kim, AS Bandeira, MX Goemans - arXiv preprint arXiv:1807.02884, 2018 - arxiv.org
We study the problem of community detection in a random hypergraph model which we call
the stochastic block model for $k$-uniform hypergraphs ($k$-SBM). We investigate the exact …

Community detection in hypergraphs, spiked tensor models, and sum-of-squares

C Kim, AS Bandeira… - … international conference on …, 2017 - ieeexplore.ieee.org
We study the problem of community detection in hypergraphs under a stochastic block model.
Similarly to how the stochastic block model in graphs suggests studying spiked random …

Locality-aware generalizable implicit neural representation

D Lee, C Kim, M Cho, WS HAN - Advances in Neural …, 2023 - proceedings.neurips.cc
Generalizable implicit neural representation (INR) enables a single continuous function, ie,
a coordinate-based neural network, to represent multiple data instances by modulating its …