6 papers
A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles
Jiayuan Wang, Farhad Pourpanah, Q. M. Jonathan Wu +1
Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as perception, prediction, planning, and control, to ensure safe and reliable navigation in co…
Compressing Multi-Task Model for Autonomous Driving via Pruning and Knowledge Distillation
Jiayuan Wang, Q. M. Jonathan Wu, Ning Zhang +2
Autonomous driving systems rely on panoptic perception to jointly handle object detection, drivable area segmentation, and lane line segmentation. Although multi-task learning is a…
RMT-PPAD: Real-time Multi-task Learning for Panoptic Perception in Autonomous Driving
Jiayuan Wang, Q. M. Jonathan Wu, Katsuya Suto +1
Autonomous driving systems rely on panoptic driving perception that requires both precision and real-time performance. In this work, we propose RMT-PPAD, a real-time, transformer-b…
Few-Shot Inspired Generative Zero-Shot Learning
Md Shakil Ahamed Shohag, Q. M. Jonathan Wu, Farhad Pourpanah
Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised cl…
SAM2Auto: Auto Annotation Using FLASH
Arash Rocky, Q. M. Jonathan Wu
Vision-Language Models (VLMs) lag behind Large Language Models due to the scarcity of annotated datasets, as creating paired visual-textual annotations is labor-intensive and expen…
One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labeling
Ali Abedi, Q. M. Jonathan Wu, Ning Zhang +1
Federated Learning (FL) is a promising approach for privacy-preserving collaborative learning. However, it faces significant challenges when dealing with domain shifts, especially…