Jongheon Jeong

papers

2,592

total citations

papers (17)

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

NEURIPS 2020arXiv

688

citations

SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation

ECCV 2022arXiv

537

citations

WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation

CVPR 2023arXiv

379

citations

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

ICLR 2025arXiv

342

citations

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

NEURIPS 2021arXiv

citations

Multi-scale Diffusion Denoised Smoothing

NEURIPS 2023arXiv

citations

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

ICLR 2025arXiv

citations

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

ICLR 2024arXiv

citations

FaceShield: Defending Facial Image against Deepfake Threats

ICCV 2025arXiv

citations

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

NEURIPS 2023arXiv

citations

Adversarial Robustification via Text-to-Image Diffusion Models

ECCV 2024arXiv

citations

Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck

CVPR 2023arXiv

citations

Collaborative Score Distillation for Consistent Visual Editing

NEURIPS 2023

citations

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

NEURIPS 2025arXiv

citations

Jongheon Jeong

papers (17)

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation

WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

M2m: Imbalanced Classification via Major-to-Minor Translation

NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation

Consistency Regularization for Certified Robustness of Smoothed Classifiers

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Multi-scale Diffusion Denoised Smoothing

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

FaceShield: Defending Facial Image against Deepfake Threats

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Adversarial Robustification via Text-to-Image Diffusion Models

Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck

Collaborative Score Distillation for Consistent Visual Editing

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

papers (17)

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation

WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

M2m: Imbalanced Classification via Major-to-Minor Translation

NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation

Consistency Regularization for Certified Robustness of Smoothed Classifiers

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Multi-scale Diffusion Denoised Smoothing

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

FaceShield: Defending Facial Image against Deepfake Threats

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Adversarial Robustification via Text-to-Image Diffusion Models

Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck

Collaborative Score Distillation for Consistent Visual Editing

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing