Aggregation of multi-stage features has been revealed to play a significant role in semantic segmentation. Unlike previous methods employing point-wise summation or concatenation for feature aggregation, this study proposes the Category Feature Transformer (CFT) that explores the flow of category embedding and transformation among multi-stage features through the prevalent multi-head attention mechanism. CFT learns unified feature embeddings for individual semantic categories from high-level features during each aggregation process and dynamically broadcasts them to high-resolution features. Integrating the proposed CFT into a typical feature pyramid structure exhibits superior performance over a broad range of backbone networks. We conduct extensive experiments on popular semantic segmentation benchmarks. Specifically, the proposed CFT obtains a compelling 55.1% mIoU with greatly reduced model parameters and computations on the challenging ADE20K dataset.
@article{arxiv.2308.05581,
title = {Category Feature Transformer for Semantic Segmentation},
author = {Quan Tang and Chuanjian Liu and Fagui Liu and Yifan Liu and Jun Jiang and Bowen Zhang and Kai Han and Yunhe Wang},
journal= {arXiv preprint arXiv:2308.05581},
year = {2023}
}