Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets
This work addresses the need for low-cost weak annotations in semantic segmentation, which is an incremental improvement for researchers and practitioners in computer vision.
The paper tackles the problem of expensive pixel-level labeling for semantic segmentation by using Constrained Dominant Sets (CDS) to generate multi-labeled full mask predictions for training a fully convolutional network, resulting in higher-quality mask predictions compared to existing methods.
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.