Video Class Agnostic Segmentation Benchmark for Autonomous Driving

TL;DR

This paper introduces a new benchmark for video class agnostic segmentation in autonomous driving, focusing on segmenting both known and unknown objects in monocular video sequences, with datasets and baseline methods provided.

Contribution

It formalizes the task of video class agnostic segmentation for autonomous driving, providing datasets, benchmarks, and baseline approaches for both open-set and motion segmentation.

Findings

Benchmark results for real-time joint panoptic and motion segmentation.

Evaluation of ego-flow suppression effects on motion segmentation.

Comparison of appearance-geometry prototypes versus contrastive learning methods.

Abstract

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/.