Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Condurache, Alexandru"'
Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving. Nowadays deep learning methods can be trained to match a pair of point clouds, given the transformation between them. However, this traini
Externí odkaz:
http://arxiv.org/abs/2409.07558
Monocular 3D lane detection has become a fundamental problem in the context of autonomous driving, which comprises the tasks of finding the road surface and locating lane markings. One major challenge lies in a flexible but robust line representation
Externí odkaz:
http://arxiv.org/abs/2406.08381
Planning the trajectory of the controlled ego vehicle is a key challenge in automated driving. As for human drivers, predicting the motions of surrounding vehicles is important to plan the own actions. Recent motion prediction methods utilize equivar
Externí odkaz:
http://arxiv.org/abs/2403.11304
To reduce the computational cost of convolutional neural networks (CNNs) for usage on resource-constrained devices, structured pruning approaches have shown promising results, drastically reducing floating-point operations (FLOPs) without substantial
Externí odkaz:
http://arxiv.org/abs/2309.17211
Automated driving has the potential to revolutionize personal, public, and freight mobility. Beside accurately perceiving the environment, automated vehicles must plan a safe, comfortable, and efficient motion trajectory. To promote safety and progre
Externí odkaz:
http://arxiv.org/abs/2308.05731
Autor:
Lust, Julia, Condurache, Alexandru P.
Publikováno v:
IJCNN 2023
Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks or out-of-d
Externí odkaz:
http://arxiv.org/abs/2307.02672
We address the problem of improving the performance and in particular the sample complexity of deep neural networks by enforcing and guaranteeing invariances to symmetry transformations rather than learning them from data. Group-equivariant convoluti
Externí odkaz:
http://arxiv.org/abs/2303.01567
Publikováno v:
Artif Intell Rev 2023
State-of-the-art deep learning models have a parameter count that reaches into the billions. Training, storing and transferring such models is energy and time consuming, thus costly. A big part of these costs is caused by training the network. Model
Externí odkaz:
http://arxiv.org/abs/2205.08099
Unstructured pruning is well suited to reduce the memory footprint of convolutional neural networks (CNNs), both at training and inference time. CNNs contain parameters arranged in $K \times K$ filters. Standard unstructured pruning (SP) reduces the
Externí odkaz:
http://arxiv.org/abs/2203.07808
Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. This makes them applicable to practically important use-cases where training data is scarce. Rathe
Externí odkaz:
http://arxiv.org/abs/2202.03967