Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets

TL;DR

This paper introduces a novel approach using Constrained Dominant Sets to generate high-quality multi-labeled masks from weak annotations, enabling effective training of semantic segmentation networks with reduced labeling costs.

Contribution

The work proposes a new method leveraging Constrained Dominant Sets for improved mask prediction in weakly supervised semantic segmentation, outperforming existing approaches.

Findings

Higher-quality mask predictions compared to previous methods

Effective training of FCNs with weak annotations

Demonstrated improved segmentation performance

Abstract

The availability of large-scale data sets is an essential pre-requisite 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.