English

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Computer Vision and Pattern Recognition 2016-11-24 v2

Abstract

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.

Keywords

Cite

@article{arxiv.1603.07485,
  title  = {Simple Does It: Weakly Supervised Instance and Semantic Segmentation},
  author = {Anna Khoreva and Rodrigo Benenson and Jan Hosang and Matthias Hein and Bernt Schiele},
  journal= {arXiv preprint arXiv:1603.07485},
  year   = {2016}
}
R2 v1 2026-06-22T13:17:46.058Z