Collaborative Video Object Segmentation by Foreground-Background Integration
arXiv:2003.08333
Abstract
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.
arXiv commentECCV 2020, Spotlight
References in corpus (4)
Cited by in corpus (7)
- Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
- Attention-guided Temporally Coherent Video Object Matting
- Associating Objects with Transformers for Video Object Segmentation
- Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
- E3D: Event-Based 3D Shape Reconstruction
- U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation
- SwiftNet: Real-time Video Object Segmentation