ML Anthology

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

Huaijia Lin, Xiaojuan Qi, Jiaya Jia
ICCV 2019
doi:10.1109/ICCV.2019.00405 /iccv/2019/lin2019iccv-agssvos/

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.

PDF ICCV Semantic Scholar

Cite

Text

Lin et al. "AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00405

Markdown

[Lin et al. "AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/lin2019iccv-agssvos/) doi:10.1109/ICCV.2019.00405

BibTeX

@inproceedings{lin2019iccv-agssvos,
  title     = {{AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation}},
  author    = {Lin, Huaijia and Qi, Xiaojuan and Jia, Jiaya},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00405},
  url       = {https://mlanthology.org/iccv/2019/lin2019iccv-agssvos/}
}