Sanghyuk Chun

SanghyukChun's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 18 papers over 1 year ago

Rethinking Spatial Dimensions of Vision Transformers

Paper • 2103.16302 • Published Mar 30, 2021 • 1

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Paper • 1905.04899 • Published May 13, 2019

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

Paper • 2303.11114 • Published Mar 20, 2023

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Paper • 2303.11916 • Published Mar 21, 2023

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

Paper • 2110.03921 • Published Oct 8, 2021 • 1

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

Paper • 2204.03359 • Published Apr 7, 2022

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

Paper • 2006.08217 • Published Jun 15, 2020

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

Paper • 2312.01998 • Published Dec 4, 2023

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

Paper • 2101.05022 • Published Jan 13, 2021

Probabilistic Embeddings for Cross-Modal Retrieval

Paper • 2101.05068 • Published Jan 13, 2021

Evaluating Weakly Supervised Object Localization Methods Right

Paper • 2001.07437 • Published Jan 21, 2020

Learning De-biased Representations with Biased Representations

Paper • 1910.02806 • Published Oct 7, 2019

An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods

Paper • 2003.03879 • Published Mar 9, 2020

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

Paper • 2110.03095 • Published Oct 6, 2021

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

Paper • 2007.04178 • Published Jul 8, 2020

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

Paper • 2106.04165 • Published Jun 8, 2021

An Extendable, Efficient and Effective Transformer-based Object Detector

Paper • 2204.07962 • Published Apr 17, 2022

Improved Probabilistic Image-Text Representations

Paper • 2305.18171 • Published May 29, 2023