Widely observed neural scaling laws, in which error falls off as a power of the training set size, model size, or both, have driven substantial performance improvements in deep …
How should we integrate representations from complementary sensors for autonomous driving? Geometry-based fusion has shown promise for perception (eg, object detection …
Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as …
J Choi, I Elezi, HJ Lee, C Farabet… - Proceedings of the …, 2021 - openaccess.thecvf.com
Active learning aims to reduce labeling costs by selecting only the most informative samples on a dataset. Few existing works have addressed active learning for object detection. Most …
Y Wu, DH Wang, XT Lu, F Yang, M Yao… - Machine Intelligence …, 2022 - Springer
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence. It …
Deep Neural Networks trained in a fully supervised fashion are the dominant technology in perception-based autonomous driving systems. While collecting large amounts of unlabeled …
Although deep learning has made great progress in recent years, the exploding economic and environmental costs of training neural networks are becoming unsustainable. To …
Abstract Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples …
Z Liu, X He - IEEE Transactions on Intelligent Transportation …, 2023 - ieeexplore.ieee.org
Real-time safety assessment of dynamic systems has recently received increasing attention. However, the performance of existing advanced approaches is often negatively affected by …