Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation

Semantic segmentation models have reached re- markable performance across various tasks. However, this perfor- mance is achieved with extremely large models, using powerful computational resources and without considering training and inference time. Real-world applications, on the other hand, necessitate models with minimal memory demands, efficient inference speed, and executable with low-resources embedded devices, such as self-driving vehicles. In this paper, we look at the challenge of real-time semantic segmentation across domains, and we train a model to act appropriately on real-world data even though it was trained on a synthetic realm. We employ a new lightweight and shallow discriminator that was specifically created for this purpose. To the best of our knowledge, we are the first to present a real-time ad- versarial approach for assessing the domain adaption problem in semantic segmentation. We tested our framework in the two stan- dard protocol: GTA5→Cityscapes and SYNTHIA→Cityscapes. Code is available at: https://github.com/taveraantonio/RTD