DEVA is a groundbreaking model in computer vision that redefines object tracking. It consists of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. DEVA outperforms end-to-end approaches in various data-scarce tasks.

2m read timeFrom ai.plainenglish.io
Post cover image
Table of contents
DEVA: Tracking Anything with Decoupled Video SegmentationPlainEnglish.io 🚀

Sort: