While propagation-based approaches have achieved state-of-the-art performance for video object segmentation, the literature lacks a fair comparison of different methods using the same settings. In this paper, we carry out an empirical study for propagation-based methods. We view these approaches from a unified perspective and conduct detailed ablation study for core methods, input cues, multi-object combination and training strategies. With careful designs, our improved end-to-end memory networks achieve a global mean of 76.1 on DAVIS 2017 val set.
@article{arxiv.1907.12769,
title = {An Empirical Study of Propagation-based Methods for Video Object Segmentation},
author = {Hengkai Guo and Wenji Wang and Guanjun Guo and Huaxia Li and Jiachen Liu and Qian He and Xuefeng Xiao},
journal= {arXiv preprint arXiv:1907.12769},
year = {2019}
}
Comments
The 2019 DAVIS Challenge on Video Object Segmentation - CVPR Workshops