Sanghyuk Chun

Orcid: 0000-0002-4533-2610

According to our database1, Sanghyuk Chun authored at least 44 papers between 2017 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Few-Shot Font Generation With Weakly Supervised Localized Representations.
IEEE Trans. Pattern Anal. Mach. Intell., March, 2024

Toward Interactive Regional Understanding in Vision-Large Language Models.
CoRR, 2024

2023
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets.
IEEE Trans. Pattern Anal. Mach. Intell., 2023

Language-only Efficient Training of Zero-shot Composed Image Retrieval.
CoRR, 2023

Longer-range Contextualized Masked Autoencoder.
CoRR, 2023

Improved Probabilistic Image-Text Representations.
CoRR, 2023

RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models.
CoRR, 2023

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion.
CoRR, 2023

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Group Generalized Mean Pooling for Vision Transformer.
CoRR, 2022

Similarity of Neural Architectures Based on Input Gradient Transferability.
CoRR, 2022

An Extendable, Efficient and Effective Transformer-based Object Detector.
CoRR, 2022

A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Dataset Condensation with Contrastive Signals.
Proceedings of the International Conference on Machine Learning, 2022

ViDT: An Efficient and Effective Fully Transformer-based Object Detector.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective.
Proceedings of the Tenth International Conference on Learning Representations, 2022

ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO.
Proceedings of the Computer Vision - ECCV 2022, 2022

Domain Generalization by Mutual-Information Regularization with Pre-trained Models.
Proceedings of the Computer Vision - ECCV 2022, 2022

Learning Fair Classifiers with Partially Annotated Group Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures.
CoRR, 2021

Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

SWAD: Domain Generalization by Seeking Flat Minima.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights.
Proceedings of the 9th International Conference on Learning Representations, 2021

Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Rethinking Spatial Dimensions of Vision Transformers.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Probabilistic Embeddings for Cross-Modal Retrieval.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Few-shot Font Generation with Localized Style Representations and Factorization.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets.
CoRR, 2020

Slowing Down the Weight Norm Increase in Momentum-based Optimizers.
CoRR, 2020

An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods.
CoRR, 2020

Learning De-biased Representations with Biased Representations.
Proceedings of the 37th International Conference on Machine Learning, 2020

Data-Driven Harmonic Filters for Audio Representation Learning.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Few-Shot Compositional Font Generation with Dual Memory.
Proceedings of the Computer Vision - ECCV 2020, 2020

Evaluating Weakly Supervised Object Localization Methods Right.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Visualizing and Understanding Self-attention based Music Tagging.
CoRR, 2019

Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling.
CoRR, 2019

Toward Interpretable Music Tagging with Self-Attention.
CoRR, 2019

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Photorealistic Style Transfer via Wavelet Transforms.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018
Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement.
CoRR, 2018

2017
A study on intelligent personalized push notification with user history.
Proceedings of the 2017 IEEE International Conference on Big Data (IEEE BigData 2017), 2017


  Loading...