The Cityscapes dataset is again part of the Robust Vision Challenge. The goal of this challenge is to foster the development of vision systems that are robust and consequently perform well on a variety of datasets with different characteristics. Towards this goal, performance is measured across a number of challenging benchmarks with different characteristics, e.g., indoors vs. outdoors, real vs. synthetic, sunny vs. bad weather, different sensors.
Methods that participate in the semantic, instance, or panoptic task need to submit their results to our evaluation server.
