Search Results for author:
Found 25 papers, 20 papers with code
FaceShield: Defending Facial Image against Deepfake Threats
The rising use of deepfakes in criminal activities presents a significant issue, inciting widespread controversy.
Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
We also find that such a fine-tuning can be done by updating a small fraction of parameters of the classifier.
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned through recent self-supervised learning methods.
Ranked #3 on
Image Generation
on ImageNet 256x256
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
Through extensive experiments, we show that our method achieves stronger protection and improved mask robustness with lower computational costs compared to the strongest baseline.
Adversarial Robustification via Text-to-Image Diffusion Models
Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data.
Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
In this paper, we focus on the alignment of recent text-to-image diffusion models, such as Stable Diffusion XL (SDXL), and find that this "reference mismatch" is indeed a significant problem in aligning these models due to the unstructured nature of visual modalities: e. g., a preference for a particular stylistic aspect can easily induce such a discrepancy.
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
To investigate this issue in depth, we introduce the Text-Image Alignment Assessment (TIA2) benchmark, which comprises a diverse collection of text prompts, images, and human annotations.
Multi-scale Diffusion Denoised Smoothing
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-trained models.
Collaborative Score Distillation for Consistent Visual Synthesis
Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities.
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
Visual anomaly classification and segmentation are vital for automating industrial quality inspection.
Ranked #1 on
zero-shot anomaly detection
on MVTec AD
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
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 one cannot prevent a model from co-adapting on such (so-called) "shortcut" signals: this makes the model fragile in various distribution shifts.
Guiding Energy-based Models via Contrastive Latent Variables
To enable the joint training of EBM and CRL, we also design a new class of latent-variable EBMs for learning the joint density of data and the contrastive latent variable.
Confidence-aware Training of Smoothed Classifiers for Certified Robustness
Under the smoothed classifiers, the fundamental trade-off between accuracy and (adversarial) robustness has been well evidenced in the literature: i. e., increasing the robustness of a classifier for an input can be at the expense of decreased accuracy for some other inputs.
NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; only unlabeled test data streams are used for continual model adaptation.
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation
Visual anomaly detection is commonly used in industrial quality inspection.
Ranked #27 on
Anomaly Detection
on VisA
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations.
OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data
Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations.
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Adversarial Robustness
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations.
Training GANs with Stronger Augmentations via Contrastive Discriminator
Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting.
Consistency Regularization for Adversarial Robustness
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks.
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Based on this, we propose a new detection score that is specific to the proposed training scheme.
Consistency Regularization for Certified Robustness of Smoothed Classifiers
A recent technique of randomized smoothing has shown that the worst-case (adversarial) $\ell_2$-robustness can be transformed into the average-case Gaussian-robustness by "smoothing" a classifier, i. e., by considering the averaged prediction over Gaussian noise.
M2m: Imbalanced Classification via Major-to-minor Translation
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion.
Ranked #43 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Training CNNs with Selective Allocation of Channels
Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy.
Selective Convolutional Units: Improving CNNs via Channel Selectivity
Bottleneck structures with identity (e. g., residual) connection are now emerging popular paradigms for designing deep convolutional neural networks (CNN), for processing large-scale features efficiently.
