Jin-Hwa Kim

Jin-Hwa Kim

Auto-generated profile, based on publicly available information

Jin-Hwa Kim

SNU AIIS

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 October 2018
Verified
Book Chapter
Closed access
PDF file
KKKyung-Min Kim
Kyung-Min Kim
SCSeong-Ho Choi
Seong-Ho Choi
JKJin-Hwa Kim
Jin-Hwa Kim
BZByoung-Tak Zhang
Byoung-Tak Zhang

1 January 2024
Verified
Conference Paper
Open access
PDF file
FZFatemeh Pesaran Zadeh
Fatemeh Pesaran Zadeh
JKJuyeon Kim
Juyeon Kim
JKJin-Hwa Kim
Jin-Hwa Kim
GKGunhee Kim
Gunhee Kim
Fatemeh Pesaran Zadeh, Juyeon Kim, Jin-Hwa Kim, Gunhee Kim. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

13 September 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
KJKim Jun-Seong
Kim Jun-Seong
MKMingyu Kim
Mingyu Kim
GKGeonU Kim
GeonU Kim
TOTae-Hyun Oh
Tae-Hyun Oh
JKJin-Hwa Kim
Jin-Hwa Kim
We introduce Fact-Hash, a novel parameter-encoding method for training on-device neural radiance fields. Neural Radiance Fields (NeRF) have proven pivotal in 3D representations, but their applications are limited due to large computational resources. On-device training can open large application fields, providing strength in communication limitations, privacy concerns, and fast adaptation to a frequently changing scene. However, challenges such as limited resources (GPU memory, storage, and power) impede their deployment. To handle this, we introduce Fact-Hash, a novel parameter-encoding merging Tensor Factorization and Hash-encoding techniques. This integration offers two benefits: the use of rich high-resolution features and the few-shot robustness. In Fact-Hash, we project 3D coordinates into multiple lower-dimensional forms (2D or 1D) before applying the hash function and then aggregate them into a single feature. Comparative evaluations against state-of-the-art methods demonstrate Fact-Hash's superior memory efficiency, preserving quality and rendering speed. Fact-Hash saves memory usage by over one-third while maintaining the PSNR values compared to previous encoding methods. The on-device experiment validates the superiority of Fact-Hash compared to alternative positional encoding methods in computational efficiency and energy consumption. These findings highlight Fact-Hash as a promising solution to improve feature grid representation, address memory constraints, and improve quality in various applications.

30 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
HLHyungyung Lee
Hyungyung Lee
DLDa Young Lee
Da Young Lee
WKWonjae Kim
Wonjae Kim
JKJin-Hwa Kim
Jin-Hwa Kim
TKTackeun Kim
Tackeun Kim
ECEdward Choi
Edward Choi
Synthetic medical data generation has opened up new possibilities in the healthcare domain, offering a powerful tool for simulating clinical scenarios, enhancing diagnostic and treatment quality, gaining granular medical knowledge, and accelerating the development of unbiased algorithms. In this context, we present a novel approach called ViewXGen, designed to overcome the limitations of existing methods that rely on general domain pipelines using only radiology reports to generate frontal-view chest X-rays. Our approach takes into consideration the diverse view positions found in the dataset, enabling the generation of chest X-rays with specific views, which marks a significant advancement in the field. To achieve this, we introduce a set of specially designed tokens for each view position, tailoring the generation process to the user's preferences. Furthermore, we leverage multi-view chest X-rays as input, incorporating valuable information from different views within the same study. This integration rectifies potential errors and contributes to faithfully capturing abnormal findings in chest X-ray generation. To validate the effectiveness of our approach, we conducted statistical analyses, evaluating its performance in a clinical efficacy metric on the MIMIC-CXR dataset. Also, human evaluation demonstrates the remarkable capabilities of ViewXGen, particularly in producing realistic view-specific X-rays that closely resemble the original images.

3 February 2023 in arXiv
Verified
Preprint
Open access
PDF file
HHHwan Heo
Hwan Heo
TKTaekyung Kim
Taekyung Kim
JLJiyoung Lee
Jiyoung Lee
JLJaewon Lee
Jaewon Lee
SKSoohyun Kim
Soohyun Kim
JKJin-Hwa Kim
Jin-Hwa Kim
Multi-resolution hash encoding has recently been proposed to reduce the computational cost of neural renderings, such as NeRF. This method requires accurate camera poses for the neural renderings of given scenes. However, contrary to previous methods jointly optimizing camera poses and 3D scenes, the naive gradient-based camera pose refinement method using multi-resolution hash encoding severely deteriorates performance. We propose a joint optimization algorithm to calibrate the camera pose and learn a geometric representation using efficient multi-resolution hash encoding. Showing that the oscillating gradient flows of hash encoding interfere with the registration of camera poses, our method addresses the issue by utilizing smooth interpolation weighting to stabilize the gradient oscillation for the ray samplings across hash grids. Moreover, the curriculum training procedure helps to learn the level-wise hash encoding, further increasing the pose refinement. Experiments on the novel-view synthesis datasets validate that our learning frameworks achieve state-of-the-art performance and rapid convergence of neural rendering, even when initial camera poses are unknown.

31 August 2021 in arXiv
Verified
Preprint
Open access
PDF file
GKGi-Cheon Kang
Gi-Cheon Kang
JPJunseok Park
Junseok Park
HLHwaran Lee
Hwaran Lee
BZByoung-Tak Zhang
Byoung-Tak Zhang
JKJin-Hwa Kim
Jin-Hwa Kim
Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic structures among dialog rounds and (2) identifying several appropriate answers to the given question. To address these challenges, we propose a Sparse Graph Learning (SGL) method to formulate visual dialog as a graph structure learning task. SGL infers inherently sparse dialog structures by incorporating binary and score edges and leveraging a new structural loss function. Next, we introduce a Knowledge Transfer (KT) method that extracts the answer predictions from the teacher model and uses them as pseudo labels. We propose KT to remedy the shortcomings of single ground-truth labels, which severely limit the ability of a model to obtain multiple reasonable answers. As a result, our proposed model significantly improves reasoning capability compared to baseline methods and outperforms the state-of-the-art approaches on the VisDial v1.0 dataset. The source code is available at https://github.com/gicheonkang/SGLKT-VisDial.