Domain Generalised Faster R-CNN
Karthik Seemakurthy, Charles Fox, Erchan Aptoula, Petra Bosilj
Abstract
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 https://github.com/karthikiitm87/domain-generalisation.git
BibTeX
@article{Seemakurthy_Fox_Aptoula_Bosilj_2023, title={Domain Generalised Faster R-CNN}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25312}, DOI={10.1609/aaai.v37i2.25312}, abstractNote={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
https://github.com/karthikiitm87/domain-generalisation.git}, number={2}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Seemakurthy, Karthik and Fox, Charles and Aptoula, Erchan and Bosilj, Petra}, year={2023}, month={Jun.}, pages={2180-2190} }