Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chengyao Wang, Shu Liu, Jingyong Su, Jiaya Jia
Abstract
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve 50.0% mIoU on COCO-5i dataset one-shot setting and 56.0% on five-shot segmentation, respectively. The code is available on the project website.
BibTeX
@inproceedings{cvpr2023_hierarchicaldens,
title = {Hierarchical Dense Correlation Distillation for Few-Shot Segmentation},
author = {Bohao Peng and Zhuotao Tian and Xiaoyang Wu and Chengyao Wang and Shu Liu and Jingyong Su and Jiaya Jia},
booktitle = {CVPR 2023},
year = {2023}
}