Video Class Agnostic Segmentation Benchmark for Autonomous Driving
This addresses a safety-critical need in autonomous driving by enabling segmentation of all objects, including those unknown during training, though it is incremental as it builds on existing segmentation approaches.
The paper tackles the problem of segmenting unknown objects in autonomous driving by formalizing video class agnostic segmentation, benchmarking baseline methods for open-set and motion segmentation tracks, and releasing public datasets and models.
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 segmentation from monocular video sequences in autonomous driving to account for unknown objects. Video class agnostic segmentation can be formulated as an open-set or a motion segmentation problem. We discuss both formulations and provide datasets and benchmark different baseline approaches for both tracks. In the motion-segmentation track we benchmark real-time joint panoptic and motion instance segmentation, and evaluate the effect of ego-flow suppression. In the open-set segmentation track we evaluate baseline methods that combine appearance, and geometry to learn prototypes per semantic class. We then compare it to a model that uses an auxiliary contrastive loss to improve the discrimination between known and unknown objects. Datasets and models are publicly released at https://msiam.github.io/vca/.