Search Results for author:
Found 17 papers, 4 papers with code
Defending Against Universal Perturbations With Shared Adversarial Training
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space.
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels.
SELF: Learning to Filter Noisy Labels with Self-Ensembling
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time.
DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision
Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels.
Does enhanced shape bias improve neural network robustness to common corruptions?
We conclude that the data augmentation caused by style-variation accounts for the improved corruption robustness and increased shape bias is only a byproduct.
Test-Time Adaptation to Distribution Shifts by Confidence Maximization and Input Transformation
This paper focuses on the fully test-time adaptation setting, where only unlabeled data from the target distribution is required.
Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
This paper focuses on the fully test-time adaptation setting, where only unlabeled data from the target distribution is required.
DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
We also argue that it is necessary for DNNs to exploit GO to overcome shortcut learning.
Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
Neural architectures based on attention such as vision transformers are revolutionizing image recognition.
Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Our approach extends the training set with an additional dataset (the source domain), which is specifically designed to facilitate learning independent representations of basic visual factors.
Multi-Attribute Open Set Recognition
While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they cannot provide explanations indicating which underlying visual attribute(s) (e. g., shape, color or background) cause a specific sample to be unknown.
Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
The success of this strategy relies heavily on the model's invariance to image pixel masking.
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features.
Zero-Shot Visual Classification with Guided Cropping
We empirically show that our approach improves zero-shot classification results across architectures and datasets, favorably for small objects.
AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models
We show that AutoCLIP outperforms baselines across a broad range of vision-language models, datasets, and prompt templates consistently and by up to 3 percent point accuracy.
Text-driven Prompt Generation for Vision-Language Models in Federated Learning
Prompt learning for vision-language models, e. g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons.
