Weakly supervised instance segmentation using multi-stage erasing refinement and saliency-guided proposals ordering

Zheng Hu, Zhi Liu, Gongyang Li, Linwei Ye, Lei Zhou, Yang Wang

Abstract

Highlights•We propose a novel weakly supervised instance segmentation framework equipped with MSER and SGPO.•We propose the Multi-Stage Erasing Refinement method to better provide location and boundary information of objects.•We propose the Saliency-Guided Proposals Ordering method to alleviate the adverse effect of background regions.•Experiments on PASCAL VOC 2012 and COCO datasets demonstrate the superiority of our method.
BibTeX
@article{hu2020weakly,
  author = {Zheng Hu and Zhi Liu and Gongyang Li and Linwei Ye and Lei Zhou and Yang Wang},
  title = {{Weakly supervised instance segmentation using multi-stage erasing refinement and saliency-guided proposals ordering}},
  journal = {J. Vis. Commun. Image Represent.},
  year = {2020},
  doi = {10.1016/j.jvcir.2020.102957},
}

Loading related content...

Figure