Search Results for author:
Found 12 papers, 6 papers with code
SparseFool: a few pixels make a big difference
Deep Neural Networks have achieved extraordinary results on image classification tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of the input data.
Multi-view shape estimation of transparent containers
The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions.
Hold me tight! Influence of discriminative features on deep network boundaries
In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates dataset features to the distance of samples to the decision boundary.
Neural Anisotropy Directions
In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers.
Towards robust sensing for Autonomous Vehicles: An adversarial perspective
Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions.
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
In this article, we provide an in-depth review of the field of adversarial robustness in deep learning, and give a self-contained introduction to its main notions.
Improving filling level classification with adversarial training
We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass.
A neural anisotropic view of underspecification in deep learning
In this work, we propose to study this problem from a geometric perspective with the aim to understand two key characteristics of neural network solutions in underspecified settings: how is the geometry of the learned function related to the data representation?
PRIME: A few primitives can boost robustness to common corruptions
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data.
Ranked #28 on
Domain Generalization
on ImageNet-C
Data augmentation with mixtures of max-entropy transformations for filling-level classification
We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification.
Robustness and invariance properties of image classifiers
We exploit the geometry of the decision boundaries of image classifiers for computing sparse perturbations very fast, and reveal a qualitative connection between adversarial examples and the data features that image classifiers learn.
Ethical Considerations for Responsible Data Curation
Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models.
