Perception systems play a crucial role in autonomous driving by reading the sensory data
and providing meaningful interpretation of the operating environment for decision-making …

Automated driving systems (ADSs) aim to improve the safety, efficiency and comfort of future
vehicles. To achieve this, ADSs use sensors to collect raw data from their environment. This …

We address the problem of out-of-distribution (OOD) detection for the task of object
detection. We show that residual convolutional layers with batch normalisation produce …

Abstract Recent developments for Semi-Supervised Object Detection (SSOD) have shown
the promise of leveraging unlabeled data to improve an object detector. However, thus far …

Open-vocabulary object detection (OVD) utilizes image-level cues to expand the linguistic
space of region proposals, thereby facilitating the detection of diverse novel classes. Recent …

Are vision-language models (VLMs) for open-vocabulary perception inherently open-set
models because they are trained on internet-scale datasets? We answer this question with a …

3D object detection is an essential part of automated driving, and deep neural networks
(DNNs) have achieved state-of-the-art performance for this task. However, deep models are …

Detecting both known and unknown objects is a fundamental skill for robot manipulation in
unstructured environments. Open-set object detection (OSOD) is a promising direction to …

We introduce powerful ideas from Hyperdimensional Computing into the challenging field of
Out-of-Distribution (OOD) detection. In contrast to many existing works that perform OOD …

A false negative in object detection describes an object that was not correctly localised and
classified by a detector. In concurrent work, we introduced five'false negative mechanisms' …