Abstract Models trained in federated settings often suffer from degraded performances and fail at generalizing, especially when facing heterogeneous scenarios. In this work, we …
J Dong, D Zhang, Y Cong, W Cong… - Proceedings of the …, 2023 - openaccess.thecvf.com
Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories …
J Miao, Z Yang, L Fan, Y Yang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Federated Learning (FL) is a distributed learning paradigm that collaboratively learns a global model across multiple clients with data privacy-preserving. Although many FL …
The incorporation of physical information in machine learning frameworks is opening and transforming many application domains. Here the learning process is augmented through …
Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world …
Connected and Automated Vehicles (CAVs) represent a rapidly growing technology in the automotive domain sector, offering promising solutions to address challenges such as traffic …
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the …
Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly …
This paper explores the emerging knowledge-driven autonomous driving technologies. Our investigation highlights the limitations of current autonomous driving systems, in particular …