b'Sanghyuk Chun'

research

∙ 05/29/2023

Improved Probabilistic Image-Text Representations

Image-Text Matching (ITM) task, a fundamental vision-language (VL) task,...

0 Sanghyuk Chun, et al. ∙

research

∙ 04/21/2023

RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models

Recently, large-scale vision-language pre-training models and visual sem...

0 Seulki Park, et al. ∙

research

∙ 04/10/2023

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Recovering 3D human mesh in the wild is greatly challenging as in-the-wi...

0 Gyeongsik Moon, et al. ∙

research

∙ 03/21/2023

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

This paper proposes a novel diffusion-based model, CompoDiff, for solvin...

0 Geonmo Gu, et al. ∙

research

∙ 03/20/2023

SeiT: Storage-Efficient Vision Training with Tokens Using 1 Storage

We need billion-scale images to achieve more generalizable and ground-br...

0 Song Park, et al. ∙

research

∙ 03/01/2023

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Many existing group fairness-aware training methods aim to achieve the g...

0 Sangwon Jung, et al. ∙

research

∙ 12/08/2022

Group Generalized Mean Pooling for Vision Transformer

Vision Transformer (ViT) extracts the final representation from either c...

0 ByungSoo Ko, et al. ∙

research

∙ 10/20/2022

Similarity of Neural Architectures Based on Input Gradient Transferability

In this paper, we aim to design a quantitative similarity function betwe...

0 Jaehui Hwang, et al. ∙

research

∙ 08/21/2022

A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective

We propose the first unified theoretical analysis of mixed sample data a...

18 Chanwoo Park, et al. ∙

research

∙ 04/07/2022

ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO

Image-Test matching (ITM) is a common task for evaluating the quality of...

0 Sanghyuk Chun, et al. ∙

research

∙ 03/21/2022

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

Domain generalization (DG) aims to learn a generalized model to an unsee...

0 Junbum Cha, et al. ∙

research

∙ 02/07/2022

Dataset Condensation with Contrastive Signals

Recent studies have demonstrated that gradient matching-based dataset sy...

0 Saehyung Lee, et al. ∙

research

∙ 12/22/2021

Few-shot Font Generation with Weakly Supervised Localized Representations

Automatic few-shot font generation aims to solve a well-defined, real-wo...

0 Song Park, et al. ∙

research

∙ 11/29/2021

Learning Fair Classifiers with Partially Annotated Group Labels

Recently, fairness-aware learning have become increasingly crucial, but ...

0 Sangwon Jung, et al. ∙

research

∙ 10/06/2021

Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective

Deep neural networks (DNNs) often rely on easy-to-learn discriminatory f...

6 Luca Scimeca, et al. ∙

research

∙ 08/24/2021

StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures

Recent powerful vision classifiers are biased towards textures, while sh...

0 Sanghyuk Chun, et al. ∙

research

∙ 06/08/2021

Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions

Effective control and prediction of dynamical systems often require appr...

0 Michael Poli, et al. ∙

research

∙ 04/02/2021

Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts

A few-shot font generation (FFG) method has to satisfy two objectives: t...

26 Song Park, et al. ∙

research

∙ 03/30/2021

Rethinking Spatial Dimensions of Vision Transformers

Vision Transformer (ViT) extends the application range of transformers f...

6 Byeongho Heo, et al. ∙

research

∙ 01/13/2021

Probabilistic Embeddings for Cross-Modal Retrieval

Cross-modal retrieval methods build a common representation space for sa...

3 Sanghyuk Chun, et al. ∙

research

∙ 01/13/2021

Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels

ImageNet has been arguably the most popular image classification benchma...

21 Sangdoo Yun, et al. ∙

research

∙ 09/23/2020

Few-shot Font Generation with Localized Style Representations and Factorization

Automatic few-shot font generation is in high demand because manual desi...

5 Song Park, et al. ∙

research

∙ 07/08/2020

Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets

Weakly-supervised object localization (WSOL) has gained popularity over ...

28 Junsuk Choe, et al. ∙

research

∙ 06/15/2020

Slowing Down the Weight Norm Increase in Momentum-based Optimizers

Normalization techniques, such as batch normalization (BN), have led to ...

16 Byeongho Heo, et al. ∙

research

∙ 05/21/2020

Few-shot Compositional Font Generation with Dual Memory

Generating a new font library is a very labor-intensive and time-consumi...

9 Junbum Cha, et al. ∙

research

∙ 03/09/2020

An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods

Despite apparent human-level performances of deep neural networks (DNN),...

13 Sanghyuk Chun, et al. ∙

research

∙ 01/21/2020

Evaluating Weakly Supervised Object Localization Methods Right

Weakly-supervised object localization (WSOL) has gained popularity over ...

7 Junsuk Choe, et al. ∙

research

∙ 11/11/2019

Visualizing and Understanding Self-attention based Music Tagging

Recently, we proposed a self-attention based music tagging model. Differ...

0 Minz Won, et al. ∙

research

∙ 10/15/2019

Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling

We propose a generic confidence-based approximation that can be plugged ...

16 YoungJoon Yoo, et al. ∙

research

∙ 10/07/2019

Learning De-biased Representations with Biased Representations

Many machine learning algorithms are trained and evaluated by splitting ...

25 Hyojin Bahng, et al. ∙

research

∙ 06/12/2019

Toward Interpretable Music Tagging with Self-Attention

Self-attention is an attention mechanism that learns a representation by...

0 Minz Won, et al. ∙

research

∙ 05/13/2019

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Regional dropout strategies have been proposed to enhance the performanc...

0 Sangdoo Yun, et al. ∙

research

∙ 03/23/2019

Photorealistic Style Transfer via Wavelet Transforms

Recent style transfer models have provided promising artistic results. H...

56 Jaejun Yoo, et al. ∙

research

∙ 12/21/2018

Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement

We present a hybrid framework that leverages the trade-off between tempo...

0 Jang-Hyun Kim, et al. ∙

Sanghyuk Chun

Featured Co-authors