QualityNet: Segmentation quality evaluation with deep convolutional networks

Abstract

This paper proposes a deep convolutional network for quality evaluation of object segmentation. In this work, we first present two large-scale datasets for object quality evaluation. The segmentation results of the proposed datasets are generated from simple and complex segmentation datasets respectively. Then, we propose three types of deep convolutional networks to learn object segmentation quality. The weighted mask layer is proposed to utilize both the information of foreground and background. One advantage of our network is that the segmentation quality is evaluated without using the groundtruth segmentation results during test period. This may help us obtain better segmentation result based on the predicted segmentation quality score. The promising results on the proposed datasets indicate the efficiency of our network.