Existing approaches focus on using class-level features to improve semantic segmentation performance. How to characterize the relationships of intra-class pixels and inter-class pixels is the key to extract the discriminative representative class-level features. In this paper, we introduce for the first time to describe intra-class variations by multiple distributions. Then, multiple distributions representation learning(\textbf{MDRL}) is proposed to augment the pixel representations for semantic segmentation. Meanwhile, we design a class multiple distributions consistency strategy to construct discriminative multiple distribution representations of embedded pixels. Moreover, we put forward a multiple distribution semantic aggregation module to aggregate multiple distributions of the corresponding class to enhance pixel semantic information. Our approach can be seamlessly integrated into popular segmentation frameworks FCN/PSPNet/CCNet and achieve 5.61\%/1.75\%/0.75\% mIoU improvements on ADE20K. Extensive experiments on the Cityscapes, ADE20K datasets have proved that our method can bring significant performance improvement.
@article{arxiv.2303.08029,
title = {Class-level Multiple Distributions Representation are Necessary for Semantic Segmentation},
author = {Jianjian Yin and Zhichao Zheng and Yanhui Gu and Junsheng Zhou and Yi Chen},
journal= {arXiv preprint arXiv:2303.08029},
year = {2023}
}