Domain generalised faster R-CNN

Seemakurthy, Karthik and Fox, Charles and Aptoula, Erchan and Bosilj, Petra (2023) Domain generalised faster R-CNN. In: 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, DC, USA

Full text not available from this repository. (Request a copy)


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
Item Type: Papers in Conference Proceedings
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Erchan Aptoula
Date Deposited: 03 Sep 2023 16:07
Last Modified: 03 Sep 2023 16:07

Actions (login required)

View Item
View Item