论文标题
通过前景 - 背景集成进行协作视频对象细分
Collaborative Video Object Segmentation by Foreground-Background Integration
论文作者
论文摘要
本文研究了嵌入学习的原则，以解决具有挑战性的半监督视频对象细分。与以前仅使用前景对象的像素探索嵌入学习的实践不同，我们认为应同样对待背景，从而通过前景 - 背景集成（CFBI）方法提出协作视频对象进行分割。我们的CFBI隐式强加了目标前景对象嵌入的特征及其相应的背景是对比度的，从而相应地促进了分割结果。通过从前景和背景嵌入的特征，我们的CFBI在参考和实例级别的预测序列之间执行匹配过程，从而使CFBI对各种对象尺度都有鲁棒性。我们对三个流行的基准测试，即戴维斯2016，戴维斯2017和YouTube-VOS进行了广泛的实验。我们的CFBI的表现（J $ F）分别为89.4％，81.9％和81.4％，表现优于所有其他最新方法。代码：https：//github.com/z-x-yang/cfbi。
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.
