Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks

Mostafa S. Ibrahim, Arash Vahdat, Mani Ranjbar, William G. Macready; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12715-12725

Abstract


Building a large image dataset with high-quality object masks for semantic segmentation is costly and time-consuming. In this paper, we introduce a principled semi-supervised framework that only use a small set of fully supervised images (having semantic segmentation labels and box labels) and a set of images with only object bounding box labels (we call it the weak-set). Our framework trains the primary segmentation model with the aid of an ancillary model that generates initial segmentation labels for the weak-set and a self-correction module that improves the generated labels during training using the increasingly accurate primary model. We introduce two variants of the self-correction module using either linear or convolutional functions. Experiments on the PASCAL VOC 2012 and Cityscape datasets show that our models trained with a small fully supervised set perform similar to, or better than, models trained with a large fully supervised set while requiring 7x less annotation effort.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Ibrahim_2020_CVPR,
author = {Ibrahim, Mostafa S. and Vahdat, Arash and Ranjbar, Mani and Macready, William G.},
title = {Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}