Predictive uncertainty estimation is an essential next step for the reliable deployment of deep object detectors in safety-critical tasks. In this work, we focus on estimating predictive …
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or …
MT Le, F Diehl, T Brunner… - 2018 21st International …, 2018 - ieeexplore.ieee.org
Object detection algorithms are essential components for perceiving the environment in safety-critical systems like automated driving. However, current state-of-the-art algorithms …
For self-driving cars that operate based on battery-generated power, detection and control are commonly performed in embedded systems to reduce power consumption. To drive …
Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and …
Object detection is arguably one of the most important and complex tasks to enable the advent of next-generation autonomous systems. Recent advancements in deep learning …
There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large …
Deployed into an open world, object detectors are prone to open-set errors, false positive detections of object classes not present in the training dataset. We propose GMM-Det, a real …
The capability to detect objects is a core part of autonomous driving. Due to sensor noise and incomplete data, perfectly detecting and localizing every object is infeasible. Therefore …