Towards knowledge-driven autonomous driving
This paper explores the emerging knowledge-driven autonomous driving technologies. Our
investigation highlights the limitations of current autonomous driving systems, in particular …
investigation highlights the limitations of current autonomous driving systems, in particular …
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives
Foundation models have indeed made a profound impact on various fields, emerging as
pivotal components that significantly shape the capabilities of intelligent systems. In the …
pivotal components that significantly shape the capabilities of intelligent systems. In the …
Merging Vision Transformers from Different Tasks and Domains
This work targets to merge various Vision Transformers (ViTs) trained on different tasks (ie,
datasets with different object categories) or domains (ie, datasets with the same categories …
datasets with different object categories) or domains (ie, datasets with the same categories …
Push-and-Pull: A General Training Framework with Differential Augmentor for Domain Generalized Point Cloud Classification
J Xu, X Ma, L Zhang, B Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
As a fundamental task of 3D perception, point cloud recognition has shown significant
progress in recent years. However, existing methods still face challenges when dealing with …
progress in recent years. However, existing methods still face challenges when dealing with …
Efficient Architecture Search for Real-Time Instance Segmentation
R Xia, D Zhang, Y Dong, J Zhao, W Liao… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Traditional CNN-based training for instance segmentation is time-consuming owing to large
datasets and complex network modules, making direct searching of architecture …
datasets and complex network modules, making direct searching of architecture …