Collaborative Video Object Segmentation by Foreground-Background Integration
It addresses the problem of accurate video object segmentation for computer vision applications, offering a novel method that improves over existing approaches.
This paper tackles semi-supervised video object segmentation by proposing the CFBI approach, which integrates foreground and background embeddings to improve segmentation robustness, achieving state-of-the-art performance of 89.4%, 81.9%, and 81.4% on DAVIS 2016, DAVIS 2017, and YouTube-VOS benchmarks.
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.