Sanghyuk Chun

发表

Learning De-biased Representations with Biased Representations

Seong Joon Oh, Jaegul Choo, Sangdoo Yun, 2019, ICML.

ROBUSTNESS USING INPUT GRADIENTS

Jaejun Yoo, Sanghyuk Chun, Ji-Hoon Kim, 2019 .

An Extendable, Efficient and Effective Transformer-based Object Detector

Ming-Hsuan Yang, Deqing Sun, Dongyoon Han, 2022, ArXiv.

SWAD: Domain Generalization by Seeking Flat Minima — Appendix

Sungrae Park, Sanghyuk Chun, Yunsung Lee, 2021 .

Toward Interpretable Music Tagging with Self-Attention pdf

Xavier Serra, Minz Won, Sanghyuk Chun, 2019, ArXiv.

Supplementary Materials: Photorealistic Style Transfer via Wavelet Transforms

Jung-Woo Ha, Jaejun Yoo, Sanghyuk Chun, 2019 .

Evaluating Weakly Supervised Object Localization Methods Right

Seong Joon Oh, Zeynep Akata, Hyunjung Shim, 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Sanghyuk Chun, Sangdoo Yun, Chanwoo Park, 2022, NeurIPS.

Dongyoon Han, Sanghyuk Chun, Byeongho Heo, 2022, ArXiv.

Dataset Condensation with Contrastive Signals

Sanghyuk Chun, Sangdoo Yun, Sung-Hoon Yoon, 2022, ICML.

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

Sungrae Park, Sanghyuk Chun, Junbum Cha, 2022, ECCV.

Group Generalized Mean Pooling for Vision Transformer

Sanghyuk Chun, Sangdoo Yun, Byeongho Heo, 2022, ArXiv.

Photorealistic Style Transfer via Wavelet Transforms

Jung-Woo Ha, Jaejun Yoo, Youngjung Uh, 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

Rethinking Spatial Dimensions of Vision Transformers pdf

Seong Joon Oh, Dongyoon Han, Sangdoo Yun, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Seong Joon Oh, Dongyoon Han, Sangdoo Yun, 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

Scalable Iterative Algorithm for Robust Subspace Clustering pdf

Jinwoo Shin, Yung-Kyun Noh, Sanghyuk Chun, 2015, ArXiv.

Probabilistic Embeddings for Cross-Modal Retrieval

Seong Joon Oh, Yannis Kalantidis, Sanghyuk Chun, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Seong Joon Oh, Sanghyuk Chun, Wonjae Kim, 2022, ECCV.

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Sanghyuk Chun, Sangdoo Yun, Wonjae Kim, 2023, ArXiv.

SWAD: Domain Generalization by Seeking Flat Minima

Sungrae Park, Sanghyuk Chun, Yunsung Lee, 2021, NeurIPS.

ViDT: An Efficient and Effective Fully Transformer-based Object Detector pdf

Deqing Sun, Ming-Hsuan Yang, Byeongho Heo, 2021, ICLR.

Dongyoon Han, Sanghyuk Chun, Byeongho Heo, 2022, ArXiv.

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

Seong Joon Oh, Gyuwan Kim, Jung-Woo Ha, 2020, ICLR.

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

Seong Joon Oh, Dongyoon Han, Sangdoo Yun, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Data-Driven Harmonic Filters for Audio Representation Learning

Xavier Serra, Minz Won, Oriol Nieto, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Hyunjung Shim, Sanghyuk Chun, Junbum Cha, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

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

Seong Joon Oh, Luca Scimeca, Sanghyuk Chun, 2021, ICLR.

Few-shot Compositional Font Generation with Dual Memory

Gayoung Lee, Sanghyuk Chun, Seonghyeon Kim, 2020, ECCV.

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

Seong Joon Oh, Atsushi Yamashita, Hajime Asama, 2021, NeurIPS.

Learning Fair Classifiers with Partially Annotated Group Labels

Sanghyuk Chun, Taesup Moon, Sangwon Jung, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Sanghyuk Chun, Sangdoo Yun, Byeongho Heo, 2023, arXiv.org.

An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods pdf

Seong Joon Oh, Dongyoon Han, Sangdoo Yun, 2020, ArXiv.

Improved Probabilistic Image-Text Representations

Sanghyuk Chun, 2023, arXiv.org.

Few-shot Font Generation with Localized Style Representations and Factorization

Hyunjung Shim, Sanghyuk Chun, Junbum Cha, 2020, AAAI.

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

Gyeongsik Moon, Sanghyuk Chun, Sangdoo Yun, 2023, arXiv.org.

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

Seong Joon Oh, Zeynep Akata, Hyunjung Shim, 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement pdf

Jung-Woo Ha, Jaejun Yoo, Sanghyuk Chun, 2018, ArXiv.

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Sanghyuk Chun, Taesup Moon, Taeeon Park, 2023, ICLR.

Improved Probabilistic Image-Text Representations

Sanghyuk Chun, 2023, ArXiv.

Dongyoon Han, Sanghyuk Chun, Byeongho Heo, 2022, 2210.11407.

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Sanghyuk Chun, Sangdoo Yun, Wonjae Kim, 2023, ArXiv.

Language-only Efficient Training of Zero-shot Composed Image Retrieval

Sanghyuk Chun, Sangdoo Yun, Wonjae Kim, 2023, ArXiv.

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

Seong Joon Oh, Sanghyuk Chun, Wonjae Kim, 2022, European Conference on Computer Vision.

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

Sanghyuk Chun, Sangdoo Yun, Jin Young Choi, 2023, 2304.10727.

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

J. Choi, Sanghyuk Chun, Sangdoo Yun, 2023, ArXiv.

Toward Interactive Regional Understanding in Vision-Large Language Models

Sanghyuk Chun, Jungbeom Lee, Sangdoo Yun, 2024, ArXiv.

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

Seong Joon Oh, Gyuwan Kim, Dongyoon Han, 2020, ICLR.

Few-shot Compositional Font Generation with Dual Memory

Sanghyuk Chun, Junbum Cha, Bado Lee, 2020, ECCV.