Domain Generalised Fully Convolutional One Stage Detection

Seemakurthy, Karthik, Bosilj, Petra, Aptoula, Erchan and Fox, Charles (2023) Domain Generalised Fully Convolutional One Stage Detection. In: International Conference on Robotics and Automation (ICRA), 29th May 2023 to 2nd June 2023., Excel London.

Full content URL:

Domain Generalised Fully Convolutional One Stage Detection
Author's accepted manuscript
ICRA_2023_CameraReadyFinal.pdf - Whole Document

Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive


Abstract—Real-time vision in robotics plays an important role in localising and recognising objects. Recently, deep learning approaches have been widely used in robotic vision. However, most of these approaches have assumed that training and test sets come from similar data distributions, which is not valid in many real world applications. This study proposes an approach to address domain generalisation (i.e. out-of distribution generalisation, OODG) where the goal is to train a model via one or more source domains, that will generalise well to unknown target domains using single stage detectors. All existing approaches which deal with OODG either use slow two stage detectors or operate under the covariate shift assumption which may not be useful for real-time robotics. This is the first paper to address domain generalisation in the context of single stage anchor free object detector FCOS without the covariate shift assumption. We focus on improving the generalisation ability of object detection by proposing new regularisation terms to address the domain shift that arises due to both classification and bounding box regression. Also, we include an additional consistency regularisation term to align the local and global level predictions. The proposed approach is implemented as a Domain Generalised Fully Convolutional One Stage (DGFCOS) detection and evaluated using four object detection datasets which provide domain metadata (GWHD, Cityscapes, BDD100K, Sim10K) where it exhibits a consistent performance improvement over the baselines and is able to run in real-time for robotics.

Keywords:Computer vision, object detection, Domain Generalisation, Agri-robotics, Autonomous driving
Subjects:H Engineering > H671 Robotics
G Mathematical and Computer Sciences > G740 Computer Vision
D Veterinary Sciences, Agriculture and related subjects > D470 Agricultural Technology
Divisions:College of Science > Lincoln Institute for Agri-Food Technology
Related URLs:
ID Code:53780
Deposited On:03 Apr 2023 14:42

Repository Staff Only: item control page