research
∙
03/26/2023
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
Visual anomaly classification and segmentation are vital for automating ...
share
research
∙
03/24/2023
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
In practical scenarios where training data is limited, many predictive s...
research
∙
03/06/2023
Guiding Energy-based Models via Contrastive Latent Variables
An energy-based model (EBM) is a popular generative framework that offer...
research
∙
12/18/2022
Confidence-aware Training of Smoothed Classifiers for Certified Robustness
Any classifier can be "smoothed out" under Gaussian noise to build a new...
research
∙
08/10/2022
Robust Continual Test-time Adaptation: Instance-aware BN and Prediction-balanced Memory
Test-time adaptation (TTA) is an emerging paradigm that addresses distri...
research
∙
07/28/2022
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation
Visual anomaly detection is commonly used in industrial quality inspecti...
research
∙
11/17/2021
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
Randomized smoothing is currently a state-of-the-art method to construct...
research
∙
03/17/2021
Training GANs with Stronger Augmentations via Contrastive Discriminator
Recent works in Generative Adversarial Networks (GANs) are actively revi...
research
∙
03/08/2021
Consistency Regularization for Adversarial Robustness
Adversarial training (AT) is currently one of the most successful method...
research
∙
07/16/2020
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Novelty detection, i.e., identifying whether a given sample is drawn fro...
research
∙
06/07/2020
Consistency Regularization for Certified Robustness of Smoothed Classifiers
A recent technique of randomized smoothing has shown that the worst-case...
research
∙
04/01/2020
M2m: Imbalanced Classification via Major-to-minor Translation
In most real-world scenarios, labeled training datasets are highly class...
research
∙
05/11/2019