274 citations · 423 across the 23 of their papers we have counts for
23 papers
StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
Younghyun Kim, Jongheon Jeong, Sangkyung Kwak +3
Learning robust representations from data often requires scale, which has led to the success of recent zero-shot models such as CLIP. However, the obtained robustness can easily be…
Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
Suhyeok Jang, Seojin Kim, Jinwoo Shin +1
The remarkable advances in deep learning have led to the emergence of many off-the-shelf classifiers, e.g., large pre-trained models. However, since they are typically trained on c…
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Sihyun Yu, Sangkyung Kwak, Huiwon Jang +4
Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of…
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
June Suk Choi, Kyungmin Lee, Jongheon Jeong +3
Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. Howev…
Adversarial Robustification via Text-to-Image Diffusion Models
Daewon Choi, Jongheon Jeong, Huiwon Jang +1
Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data. In the recent paradigm of adopti…
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
Kyuyoung Kim, Jongheon Jeong, Minyong An +4
Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimiz…
Multi-scale Diffusion Denoised Smoothing
Jongheon Jeong, Jinwoo Shin
Along with recent diffusion models, randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale, e.g., those of large pre…
Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder
Huiwon Jang, Jihoon Tack, Daewon Choi +2
Despite its practical importance across a wide range of modalities, recent advances in self-supervised learning (SSL) have been primarily focused on a few well-curated domains, e.g…
Collaborative Score Distillation for Consistent Visual Synthesis
Subin Kim, Kyungmin Lee, June Suk Choi +3
Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting…
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
Jongheon Jeong, Yang Zou, Taewan Kim +3
Visual anomaly classification and segmentation are vital for automating industrial quality inspection. The focus of prior research in the field has been on training custom models f…
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
Jongheon Jeong, Sihyun Yu, Hankook Lee +1
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that on…
Guiding Energy-based Models via Contrastive Latent Variables
Hankook Lee, Jongheon Jeong, Sejun Park +1
An energy-based model (EBM) is a popular generative framework that offers both explicit density and architectural flexibility, but training them is difficult since it is often unst…
Confidence-aware Training of Smoothed Classifiers for Certified Robustness
Jongheon Jeong, Seojin Kim, Jinwoo Shin
Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to -adversarial perturbations, viz., by averaging its prediction…
NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
Taesik Gong, Jongheon Jeong, Taewon Kim +3
Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; on…
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation
Yang Zou, Jongheon Jeong, Latha Pemula +2
Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pr…
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
Jongheon Jeong, Sejun Park, Minkyu Kim +3
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against -adversarial perturbations. Under the…
OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data
Jongjin Park, Sukmin Yun, Jongheon Jeong +1
Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one a…
Training GANs with Stronger Augmentations via Contrastive Discriminator
Jongheon Jeong, Jinwoo Shin
Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is…
Consistency Regularization for Adversarial Robustness
Jihoon Tack, Sihyun Yu, Jongheon Jeong +3
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfittin…
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Jihoon Tack, Sangwoo Mo, Jongheon Jeong +1
Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have bee…
Consistency Regularization for Certified Robustness of Smoothed Classifiers
Jongheon Jeong, Jinwoo Shin
A recent technique of randomized smoothing has shown that the worst-case (adversarial) -robustness can be transformed into the average-case Gaussian-robustness by "smoothin…
M2m: Imbalanced Classification via Major-to-minor Translation
Jaehyung Kim, Jongheon Jeong, Jinwoo Shin
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this pa…
Training CNNs with Selective Allocation of Channels
Jongheon Jeong, Jinwoo Shin
Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in…