Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps

Yuk Heo, Yeong Jun Koh, Chang-Su Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 7322-7330

Abstract


We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. First, we design the reliability-based attention module to analyze the reliability of multiple annotated frames. Second, we develop the intersection-aware propagation module to propagate segmentation results to neighboring frames. Third, we introduce the GIS mechanism for a user to select unsatisfactory frames quickly with less effort. Experimental results demonstrate that the proposed algorithm provides more accurate segmentation results at a faster speed than conventional algorithms. Codes are available at https://github.com/yuk6heo/GIS-RAmap.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Heo_2021_CVPR, author = {Heo, Yuk and Koh, Yeong Jun and Kim, Chang-Su}, title = {Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {7322-7330} }