Litcius/Paper detail

Tracking Anything with Decoupled Video Segmentation

Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander G. Schwing, Joon‐Young Lee

2023153 citationsDOI

Abstract

Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To ‘track anything’ without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation. Code is available at: hkchengrex.github.io/Tracking-Anything-with-DEVA.

Topics & Concepts

SegmentationComputer scienceArtificial intelligenceTask (project management)Scale-space segmentationComputer visionSegmentation-based object categorizationVideo trackingImage segmentationObject (grammar)Tracking (education)VocabularyPattern recognition (psychology)PsychologyEconomicsPhilosophyManagementPedagogyLinguisticsMultimodal Machine Learning ApplicationsVisual Attention and Saliency DetectionDomain Adaptation and Few-Shot Learning
Tracking Anything with Decoupled Video Segmentation | Litcius