Introspection of dnn-based perception functions in automated driving systems: State-of-the-art and open research challenges

HY Yatbaz, M Dianati… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
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 …

Toward ensuring safety for autonomous driving perception: standardization progress, research advances, and perspectives

C Sun, R Zhang, Y Lu, Y Cui, Z Deng… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
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 …

Open-set semi-supervised object detection

YC Liu, CY Ma, X Dai, J Tian, P Vajda, Z He… - European Conference on …, 2022 - Springer
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 …

Introspection of 2d object detection using processed neural activation patterns in automated driving systems

HY Yatbaz, M Dianati, K Koufos… - Proceedings of the …, 2023 - openaccess.thecvf.com
While deep neural network (DNN) models have become extremely popular for object
detection in automated driving systems (ADS), the dynamic and varied nature of the road …

CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection

W Li, X Liu, J Ma, Y Yuan - European Conference on Computer Vision, 2024 - Springer
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 …

Open-set recognition in the age of vision-language models

D Miller, N Sünderhauf, A Kenna, K Mason - European Conference on …, 2024 - Springer
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 …

SAFE: Sensitivity-aware features for out-of-distribution object detection

S Wilson, T Fischer, F Dayoub… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Out-of-distribution detection for lidar-based 3d object detection

C Huang, V Abdelzad, CG Mannes… - 2022 IEEE 25th …, 2022 - ieeexplore.ieee.org
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 …

Hyperdimensional feature fusion for out-of-distribution detection

S Wilson, T Fischer, N Sünderhauf… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Bayesian deep learning for affordance segmentation in images

L Mur-Labadia, R Martinez-Cantin… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Affordances are a fundamental concept in robotics since they relate available actions for an
agent depending on its sensory-motor capabilities and the environment. We present a novel …