Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts the global context from a categorical perspective. This class-level context describes the overall representation of each class in an image. We further propose a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel. Based on the ACF module, we introduce a coarse-to-fine segmentation network, called Attentional Class Feature Network (ACFNet), which can be composed of an ACF module and any off-the-shell segmentation network (base network). In this paper, we use two types of base networks to evaluate the effectiveness of ACFNet. We achieve new state-of-the-art performance of 81.85% mIoU on Cityscapes dataset with only finely annotated data used for training.
@article{arxiv.1909.09408,
title = {ACFNet: Attentional Class Feature Network for Semantic Segmentation},
author = {Fan Zhang and Yanqin Chen and Zhihang Li and Zhibin Hong and Jingtuo Liu and Feifei Ma and Junyu Han and Errui Ding},
journal= {arXiv preprint arXiv:1909.09408},
year = {2019}
}