Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation
This work addresses traffic forecasting challenges for urban planners and researchers, but it is incremental as it builds on existing U-Net methods with domain adaptation.
The authors tackled traffic prediction under COVID-19-induced temporal domain shifts by using U-Net with pre-trained encoders and domain adaptation techniques, achieving third place in the Traffic4Cast 2021 competition.
In this technical report, we present our solution to the Traffic4Cast 2021 Core Challenge, in which participants were asked to develop algorithms for predicting a traffic state 60 minutes ahead, based on the information from the previous hour, in 4 different cities. In contrast to the previously held competitions, this year's challenge focuses on the temporal domain shift in traffic due to the COVID-19 pandemic. Following the past success of U-Net, we utilize it for predicting future traffic maps. Additionally, we explore the usage of pre-trained encoders such as DenseNet and EfficientNet and employ multiple domain adaptation techniques to fight the domain shift. Our solution has ranked third in the final competition. The code is available at https://github.com/jbr-ai-labs/traffic4cast-2021.