Search Results for author:
Found 11 papers, 6 papers with code
Prototype-based Neural Network Layers: Incorporating Vector Quantization
Neural networks currently dominate the machine learning community and they do so for good reasons.
Robustness of Generalized Learning Vector Quantization Models against Adversarial Attacks
The evaluation suggests that both Generalized LVQ and Generalized Tangent LVQ have a high base robustness, on par with the current state-of-the-art in robust neural network methods.
Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components
The decomposition of objects into generic components combined with the probabilistic reasoning provides by design a clear interpretation of the classification decision process.
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms
Current certification methods are computationally expensive and limited to attacks that optimize the manipulation with respect to a norm.
Radar Artifact Labeling Framework (RALF): Method for Plausible Radar Detections in Datasets
RALF provides plausibility labels for radar raw detections, distinguishing between artifacts and targets.
Provident Vehicle Detection at Night: The PVDN Dataset
As humans, we intuitively assume oncoming vehicles before the vehicles are actually physically visible by detecting light reflections caused by their headlamps.
A Dataset for Provident Vehicle Detection at Night
In this paper, we study the problem of how to map this intuitive human behavior to computer vision algorithms to detect oncoming vehicles at night just from the light reflections they cause by their headlights.
Provident Vehicle Detection at Night for Advanced Driver Assistance Systems
To demonstrate the usefulness of such an algorithm, the proposed algorithm is deployed in a test vehicle to use the detected light artifacts to control the glare-free high beam system proactively.
Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night
We show that this approach allows for an automated derivation of different object representations, such as binary maps or bounding boxes so that detection models can be trained on different annotation variants and the problem of providently detecting vehicles at night can be tackled from different perspectives.
A Human-Centric Assessment Framework for AI
Inspired by the Turing test, we introduce a human-centric assessment framework where a leading domain expert accepts or rejects the solutions of an AI system and another domain expert.
Robust Text Classification: Analyzing Prototype-Based Networks
Downstream applications often require text classification models to be accurate, robust, and interpretable.
