Video Class Agnostic Segmentation Benchmark for Autonomous Driving
Video Class Agnostic Segmentation Benchmark for Autonomous Driving
Semantic segmentation approaches are typically trained on large-scale data with a closed finite set of known classes without considering unknown objects. In certain safety-critical robotics applications, especially autonomous driving, it is important to segment all objects, including those unknown at training time. We formalize the task of video class agnostic …