Search Results for author: Youngjung Uh

Found 25 papers, 15 papers with code

Semantic Image Synthesis with Unconditional Generator

no code implementations NeurIPS 2023 JungWoo Chae, Hyunin Cho, Sooyeon Go, Kyungmook Choi, Youngjung Uh

The feature rearranger learns to rearrange original feature maps to match the shape of the proxy masks that are either from the original sample itself or from random samples.

Image Generation Semantic Segmentation

Visual Style Prompting with Swapping Self-Attention

1 code implementation20 Feb 2024 Jaeseok Jeong, Junho Kim, Yunjey Choi, Gayoung Lee, Youngjung Uh

Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a consistent style, requiring costly fine-tuning or often inadequately transferring the visual elements due to content leakage.

Denoising Style Transfer +1

Attribute Based Interpretable Evaluation Metrics for Generative Models

1 code implementation26 Oct 2023 Dongkyun Kim, Mingi Kwon, Youngjung Uh

In this context, we propose a new evaluation protocol that measures the divergence of a set of generated images from the training set regarding the distribution of attribute strengths as follows.

Attribute

Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos

1 code implementation20 Oct 2023 Seoha Kim, Jeongmin Bae, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh

Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos.

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.

Disentanglement

AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks

1 code implementation ICCV 2023 Kibeom Hong, Seogkyu Jeon, Junsoo Lee, Namhyuk Ahn, Kunhee Kim, Pilhyeon Lee, Daesik Kim, Youngjung Uh, Hyeran Byun

To deliver the artistic expression of the target style, recent studies exploit the attention mechanism owing to its ability to map the local patches of the style image to the corresponding patches of the content image.

Semantic correspondence Style Transfer

Unsupervised Discovery of Semantic Latent Directions in Diffusion Models

no code implementations24 Feb 2023 Yong-Hyun Park, Mingi Kwon, Junghyo Jo, Youngjung Uh

Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space.

Attribute

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 Models already have a Semantic Latent Space

1 code implementation20 Oct 2022 Mingi Kwon, Jaeseok Jeong, Youngjung Uh

To address the problem, we propose asymmetric reverse process (Asyrp) which discovers the semantic latent space in frozen pretrained diffusion models.

Image Manipulation

LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data

1 code implementation CVPR 2023 JiHye Park, Sunwoo Kim, Soohyun Kim, Seokju Cho, Jaejun Yoo, Youngjung Uh, Seungryong Kim

Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image.

Translation Unsupervised Image-To-Image Translation

Feature Statistics Mixing Regularization for Generative Adversarial Networks

1 code implementation CVPR 2022 Junho Kim, Yunjey Choi, Youngjung Uh

In generative adversarial networks, improving discriminators is one of the key components for generation performance.

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

ArrowGAN : Learning to Generate Videos by Learning Arrow of Time

no code implementations11 Jan 2021 Kibeom Hong, Youngjung Uh, Hyeran Byun

Training GANs on videos is even more sophisticated than on images because videos have a distinguished dimension: time.

Conditional Image Generation Video Generation

Contrastive Attention Maps for Self-Supervised Co-Localization

no code implementations ICCV 2021 Minsong Ki, Youngjung Uh, Junsuk Choe, Hyeran Byun

The goal of unsupervised co-localization is to locate the object in a scene under the assumptions that 1) the dataset consists of only one superclass, e. g., birds, and 2) there are no human-annotated labels in the dataset.

Representation Learning

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

In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization

1 code implementation25 Sep 2020 Minsong Ki, Youngjung Uh, Wonyoung Lee, Hyeran Byun

Furthermore, we propose foreground consistency loss that penalizes earlier layers producing noisy attention regarding the later layer as a reference to provide them with a sense of backgroundness.

Contrastive Learning Object +1

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights

4 code implementations ICLR 2021 Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha

Because of the scale invariance, this modification only alters the effective step sizes without changing the effective update directions, thus enjoying the original convergence properties of GD optimizers.

Audio Classification Image Classification +3

Rethinking the Truly Unsupervised Image-to-Image Translation

1 code implementation ICCV 2021 Kyungjune Baek, Yunjey Choi, Youngjung Uh, Jaejun Yoo, Hyunjung Shim

To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translates input images into the estimated domains.

Translation Unsupervised Image-To-Image Translation

Reliable Fidelity and Diversity Metrics for Generative Models

2 code implementations ICML 2020 Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo

In this paper, we show that even the latest version of the precision and recall metrics are not reliable yet.

Image Generation

StarGAN v2: Diverse Image Synthesis for Multiple Domains

14 code implementations CVPR 2020 Yunjey Choi, Youngjung Uh, Jaejun Yoo, Jung-Woo Ha

A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.

Fundus to Angiography Generation Multimodal Unsupervised Image-To-Image Translation +1

Background Suppression Network for Weakly-supervised Temporal Action Localization

2 code implementations22 Nov 2019 Pilhyeon Lee, Youngjung Uh, Hyeran Byun

This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately.

Weakly Supervised Action Localization Weakly-supervised Temporal Action Localization +1

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