Loading [a11y]/accessibility-menu.js
Scalable Multi-Task Learning R-CNN for Object Detection in Autonomous Driving | IEEE Conference Publication | IEEE Xplore

Scalable Multi-Task Learning R-CNN for Object Detection in Autonomous Driving


Abstract:

Multi-task learning (MTL) is a rapidly growing field in the world of autonomous vehicles, particularly in the area of computer vision. Autonomous vehicles are heavily rel...Show More

Abstract:

Multi-task learning (MTL) is a rapidly growing field in the world of autonomous vehicles, particularly in the area of computer vision. Autonomous vehicles are heavily reliant on computer vision technology for tasks such as object detection, object segmentation, and object tracking. The complexity of sensor data and the multiple tasks involved in autonomous driving can make it challenging to design effective systems. MTL addresses these challenges by training a single model to perform multiple tasks simultaneously, utilizing shared representations to learn common concepts between a group of related tasks, and improving data efficiency. In this paper, we propose a scalable MTL system for object detection that can be used to construct any MTL network with different scales and shapes. The proposed system is an extension of the Mask R-CNN. It is designed to overcome the limitations of learning multiple objects in multi-label learning. We have a typical network and evaluated its performance on the Berkeley Deep Drive 100KBDD100k dataset. The experimental results demonstrate that the proposed MTL network outperforms a base single-task network, Mask RCNN, in terms of mean average precision at 50 (mAP50). Furthermore, we have also conducted a comparison with the existing representative approaches.
Date of Conference: 19-23 June 2023
Date Added to IEEE Xplore: 21 July 2023
ISBN Information:

ISSN Information:

Conference Location: Marrakesh, Morocco

Funding Agency:


References

References is not available for this document.