Domain Generalised Faster R-CNN

Seemakurthy, Karthik, Fox, Charles, Aptoula, Erchan and Bosilj, Petra (2023) Domain Generalised Faster R-CNN. In: The 37th AAAI conference on Artificial Intelligence, 7th Feb 2023 to 14th Feb 2023, Walter E Convention Centre, Washington DC.

Domain Generalised Faster R-CNN
This document is the camera ready version which got accepted at AAAI 2023.
PDF2CompatableVersion.pdf - Whole Document

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


Domain generalisation (i.e. out-of-distribution generalisation) is an open problem in machine learning, where the goal is to train a model via one or more source domains, that will generalise well to unknown target domains. While the topic is attracting increasing interest, it has not been studied in detail in the context of object detection. The established approaches all operate under the covariate shift assumption, where the conditional distributions are assumed to be approximately equal across source domains. This is the first paper to address domain generalisation in the context of object detection, with a rigorous mathematical analysis of domain shift, 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 Faster R-CNN 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. All the codes for replicating the results in this paper can be found at

Keywords:Computer Vision, Object Detection, Domain Generalisation
Subjects:H Engineering > H670 Robotics and Cybernetics
D Veterinary Sciences, Agriculture and related subjects > D400 Agriculture
D Veterinary Sciences, Agriculture and related subjects > D470 Agricultural Technology
Divisions:College of Science > Lincoln Institute for Agri-Food Technology
ID Code:53771
Deposited On:22 May 2023 13:00

Repository Staff Only: item control page