RANet: Ranking Attention Network for Fast Video Object Segmentation

Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, Ling Shao; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 3978-3987

Abstract


Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restricts their practicality. Matching based and propagation based methods run at a faster speed by avoiding OL techniques. However, they are limited by sub-optimal accuracy, due to mismatching and drifting problems. In this paper, we develop a real-time yet very accurate Ranking Attention Network (RANet) for VOS. Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner. To better utilize the similarity maps, we propose a novel ranking attention module, which automatically ranks and selects these maps for fine-grained VOS performance. Experiments on DAVIS16 and DAVIS17 datasets show that our RANet achieves the best speed-accuracy trade-off, e.g., with 33 milliseconds per frame and J&F=85.5% on DAVIS16. With OL, our RANet reaches J&F=87.1% on DAVIS16, exceeding state-of-the-art VOS methods. The code can be found at https://github.com/Storife/RANet.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Wang_2019_ICCV,
author = {Wang, Ziqin and Xu, Jun and Liu, Li and Zhu, Fan and Shao, Ling},
title = {RANet: Ranking Attention Network for Fast Video Object Segmentation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}