AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation

Huaijia Lin, Xiaojuan Qi, Jiaya Jia; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 3949-3957

Abstract


Most video object segmentation approaches process objects separately. This incurs high computational cost when multiple objects exist. In this paper, we propose AGSS-VOS to segment multiple objects in one feed-forward path via instance-agnostic and instance-specific modules. Information from the two modules is fused via an attention-guided decoder to simultaneously segment all object instances in one path. The whole framework is end-to-end trainable with instance IoU loss. Experimental results on Youtube- VOS and DAVIS-2017 dataset demonstrate that AGSS-VOS achieves competitive results in terms of both accuracy and efficiency.

Related Material


[pdf]
[bibtex]
@InProceedings{Lin_2019_ICCV,
author = {Lin, Huaijia and Qi, Xiaojuan and Jia, Jiaya},
title = {AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}