Search Results for author: Hyunsu Kim

Found 19 papers, 8 papers with code

Fast Ensembling with Diffusion Schrödinger Bridge

1 code implementation24 Apr 2024 Hyunsu Kim, Jongmin Yoon, Juho Lee

Deep Ensemble (DE) approach is a straightforward technique used to enhance the performance of deep neural networks by training them from different initial points, converging towards various local optima.

Sequential Data Generation with Groupwise Diffusion Process

no code implementations2 Oct 2023 Sangyun Lee, Gayoung Lee, Hyunsu Kim, Junho Kim, Youngjung Uh

We present the Groupwise Diffusion Model (GDM), which divides data into multiple groups and diffuses one group at one time interval in the forward diffusion process.


Probabilistic Imputation for Time-series Classification with Missing Data

1 code implementation13 Aug 2023 SeungHyun Kim, Hyunsu Kim, Eunggu Yun, Hwangrae Lee, Jaehun Lee, Juho Lee

In this paper, we propose a novel probabilistic framework for classification with multivariate time series data with missing values.

Imputation Time Series +1

User-friendly Image Editing with Minimal Text Input: Leveraging Captioning and Injection Techniques

no code implementations5 Jun 2023 Sunwoo Kim, Wooseok Jang, Hyunsu Kim, Junho Kim, Yunjey Choi, Seungryong Kim, Gayeong Lee

From the users' standpoint, prompt engineering is a labor-intensive process, and users prefer to provide a target word for editing instead of a full sentence.

Prompt Engineering Sentence

Regularizing Towards Soft Equivariance Under Mixed Symmetries

no code implementations1 Jun 2023 Hyunsu Kim, Hyungi Lee, Hongseok Yang, Juho Lee

The key component of our method is what we call equivariance regularizer for a given type of symmetries, which measures how much a model is equivariant with respect to the symmetries of the type.

Motion Forecasting

Context-Preserving Two-Stage Video Domain Translation for Portrait Stylization

no code implementations30 May 2023 Doyeon Kim, Eunji Ko, Hyunsu Kim, Yunji Kim, Junho Kim, Dongchan Min, Junmo Kim, Sung Ju Hwang

Portrait stylization, which translates a real human face image into an artistically stylized image, has attracted considerable interest and many prior works have shown impressive quality in recent years.


Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance

1 code implementation26 Feb 2023 Yoonjeon Kim, Hyunsu Kim, Junho Kim, Yunjey Choi, Eunho Yang

With the advantages of fast inference and human-friendly flexible manipulation, image-agnostic style manipulation via text guidance enables new applications that were not previously available.


BallGAN: 3D-aware Image Synthesis with a Spherical Background

no code implementations ICCV 2023 Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun, Youngjung Uh

To solve this problem, we propose to approximate the background as a spherical surface and represent a scene as a union of the foreground placed in the sphere and the thin spherical background.

3D-Aware Image Synthesis

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

no code implementations CVPR 2023 Gyeongman Kim, Hajin Shim, Hyunsu Kim, Yunjey Choi, Junho Kim, Eunho Yang

Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face video editing task.

Video Editing

Generator Knows What Discriminator Should Learn in Unconditional GANs

1 code implementation27 Jul 2022 Gayoung Lee, Hyunsu Kim, Junho Kim, Seonghyeon Kim, Jung-Woo Ha, Yunjey Choi

Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps.

Conditional Image Generation Unconditional Image Generation

Memory Efficient Patch-based Training for INR-based GANs

no code implementations4 Jul 2022 Namwoo Lee, Hyunsu Kim, Gayoung Lee, Sungjoo Yoo, Yunjey Choi

However, training existing approaches require a heavy computational cost proportional to the image resolution, since they compute an MLP operation for every (x, y) coordinate.

Image Outpainting Super-Resolution

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

1 code implementation ICLR 2022 Sihyun Yu, Jihoon Tack, Sangwoo Mo, Hyunsu Kim, Junho Kim, Jung-Woo Ha, Jinwoo Shin

In this paper, we found that the recent emerging paradigm of implicit neural representations (INRs) that encodes a continuous signal into a parameterized neural network effectively mitigates the issue.

Generative Adversarial Network Video Generation

Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing

1 code implementation CVPR 2021 Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo, Youngjung Uh

Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder.

Image Manipulation valid

Deep Hedging, Generative Adversarial Networks, and Beyond

no code implementations5 Mar 2021 Hyunsu Kim

This paper introduces a potential application of deep learning and artificial intelligence in finance, particularly its application in hedging.

Time Series Time Series Analysis

A StyleMap-Based Generator for Real-Time Image Projection and Local Editing

no code implementations1 Jan 2021 Hyunsu Kim, Yunjey Choi, Junho Kim, Sungjoo Yoo, Youngjung Uh

State-of-the-art GAN-based methods for editing real images suffer from time-consuming operations in projecting real images to latent vectors.

Image Manipulation

Adaptive Strategy for Resetting a Non-stationary Markov Chain during Learning via Joint Stochastic Approximation

no code implementations pproximateinference AABI Symposium 2021 Hyunsu Kim, Juho Lee, Hongseok Yang

The non-stationary kernel problem refers to the degraded performance of the algorithm due to the constant change of the transition kernel of the chain throughout the run of the algorithm.

Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss

2 code implementations ICCV 2019 Hyunsu Kim, Ho Young Jhoo, Eunhyeok Park, Sungjoo Yoo

A GAN approach is proposed, called Tag2Pix, of line art colorization which takes as input a grayscale line art and color tag information and produces a quality colored image.

Line Art Colorization TAG

Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach

no code implementations22 Apr 2019 Ki Hyun Tae, Yuji Roh, Young Hun Oh, Hyunsu Kim, Steven Euijong Whang

As machine learning is used in sensitive applications, it becomes imperative that the trained model is accurate, fair, and robust to attacks.

BIG-bench Machine Learning Fairness +1

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