One-Shot Video Object Segmentation

Code

• github.com/kmaninis/OSVOS-caffe
  tf★ 170
• github.com/Mind23-2/MindCode-5/tree/main/OSVOS
  mindspore★ 0
• github.com/xiuyu0000/new_papers_codes/tree/main/OSVOS
  mindspore★ 0
• github.com/code-implementation1/Code6/tree/main/OSVOS
  mindspore★ 0
• github.com/scaelles/OSVOS-TensorFlow
  tf★ 0
• github.com/kmaninis/OSVOS-PyTorch
  pytorch★ 0
• github.com/2023-MindSpore-1/ms-code-215/tree/main/OSVOS
  mindspore★ 0
• github.com/MS-Mind/MS-Code-06/tree/main/OSVOS
  mindspore★ 0

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%).

Tasks

Benchmark Results

Reproductions