Collaborative Video Object Segmentation by Foreground-Background Integration

2020-03-18 · ECCV 2020 8 · Zongxin Yang, Yunchao Wei, Yi Yang

This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Different from previous practices that only explore the embedding learning using pixels from foreground object (s), we consider background should be equally treated and thus propose Collaborative video object segmentation by Foreground-Background Integration (CFBI) approach. Our CFBI implicitly imposes the feature embedding from the target foreground object and its corresponding background to be contrastive, promoting the segmentation results accordingly. With the feature embedding from both foreground and background, our CFBI performs the matching process between the reference and the predicted sequence from both pixel and instance levels, making the CFBI be robust to various object scales. We conduct extensive experiments on three popular benchmarks, i.e., DAVIS 2016, DAVIS 2017, and YouTube-VOS. Our CFBI achieves the performance (J$F) of 89.4%, 81.9%, and 81.4%, respectively, outperforming all the other state-of-the-art methods. Code: https://github.com/z-x-yang/CFBI.

📄 PDF Abstract BibTeX arXiv:2003.08333

Code (2)

z-x-yang/CFBI 공식 구현 pytorch

PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/segmentation/cfbi.md paddle

Tasks

ObjectOne-shot visual object segmentation Segmentation Semantic Segmentation Semi-Supervised Video Object Segmentation Video Object Segmentation Video Semantic Segmentation

Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration

2020-10-13 · Zongxin Yang, Yunchao Wei, Yi Yang

This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Unlike previous practices that focus on exploring the embedding learning of foreground obj…

Object One-shot visual object segmentation Segmentation Semantic Segmentation+3

Ensemble Video Object Cut in Highly Dynamic Scenes

2013-06-01 · CVPR 2013 6 · Xiaobo Ren, Tony X. Han, Zhihai He

We consider video object cut as an ensemble of framelevel background-foreground object classifiers which fuses information across frames and refine their segmentation results in a collaborative and iterative manner. Our …

Change Detection Object Segmentation Semantic Segmentation

Co-attention Propagation Network for Zero-Shot Video Object Segmentation

2023-04-08 · Gensheng Pei, Yazhou Yao, Fumin Shen, Dan Huang 외

Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects. However, existing ZS-VOS methods often struggle to distinguish between foregro…

Decoder Optical Flow Estimation Semantic Segmentation Video Object Segmentation+2

Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network

2017-07-24 · Xu Zhao, Yingying Chen, Ming Tang, Jinqiao Wang

Foreground segmentation in video sequences is a classic topic in computer vision. Due to the lack of semantic and prior knowledge, it is difficult for existing methods to deal with sophisticated scenes well. Therefore, i…

Decoder Foreground Segmentation Segmentation

Joint Motion Segmentation and Background Estimation in Dynamic Scenes

2014-06-01 · CVPR 2014 6 · Adeel Mumtaz, Weichen Zhang, Antoni B. Chan

We propose a joint foreground-background mixture model (FBM) that simultaneously performs background estimation and motion segmentation in complex dynamic scenes. Our FBM consist of a set of location-specific dynamic tex…

Motion Segmentation Segmentation