One-Shot Video Object Segmentation

November 16, 2016 · Entered Twilight · 🏛 Computer Vision and Pattern Recognition

"No code URL or promise found in abstract"
"Code repo scraped from project page (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: DAVIS, LICENSE, README.md, dataset.py, doc, models, osvos.py, osvos_demo.py, osvos_parent_demo.py, requirements.txt, train_parent.txt

Authors Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc Van Gool arXiv ID 1611.05198 Category cs.CV: Computer Vision Citations 971 Venue Computer Vision and Pattern Recognition Repository https://github.com/scaelles/OSVOS-TensorFlow ⭐ 440 Last Checked 7 days ago

Abstract

This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).