Junsuk Choe

papers

1,267

total citations

papers (12)

Rethinking Spatial Dimensions of Vision Transformers

ICCV 2021arXiv

700

citations

Evaluating Weakly Supervised Object Localization Methods Right

CVPR 2020arXiv

195

citations

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

CVPR 2021arXiv

164

citations

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models

AAAI 2025arXiv

citations

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning

ICML 2025arXiv

citations

Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts

ICCV 2023arXiv

citations

Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning

COLM 2025arXiv

citations

Contrastive Attention Maps for Self-Supervised Co-Localization

ICCV 2021

citations

Junsuk Choe

papers (12)

Rethinking Spatial Dimensions of Vision Transformers

Evaluating Weakly Supervised Object Localization Methods Right

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data

Normalization Matters in Weakly Supervised Object Localization

Keep CALM and Improve Visual Feature Attribution

Weakly Supervised Semantic Segmentation for Driving Scenes

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning

Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts

Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning

Contrastive Attention Maps for Self-Supervised Co-Localization

papers (12)

Rethinking Spatial Dimensions of Vision Transformers

Evaluating Weakly Supervised Object Localization Methods Right

Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels

Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data

Normalization Matters in Weakly Supervised Object Localization

Keep CALM and Improve Visual Feature Attribution

Weakly Supervised Semantic Segmentation for Driving Scenes

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning

Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts

Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning

Contrastive Attention Maps for Self-Supervised Co-Localization