Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets


ICIAP 2019, Trento, Italy, 9 - 12 September 2019 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1007/978-3-030-30645-8_39
  • City: Trento
  • Country: Italy
  • Keywords: Semantic image segmentation, Weak training set annotations, Dominant sets, Constrained Dominant Sets, Weakly supervised semantic segmentation


The availability of large-scale data sets is an essential prerequisite for deep learning based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using low-cost weak annotations has been an attractive research problem in recent years. In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for semantic segmentation. Our experimental results show that using CDS's yields higher-quality mask predictions compared to methods that have been adopted in the literature for the same purpose.