Jiaya Jia, Zhuotao Tian, Xiaoyang Wu, Jingyong Su, Shu Liu, Bohao Peng, Chengyao Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 selfattention 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 finegrained segmentation. Our method performs decently in experiments. We achieve 50.0% mIoU on COCO-20 i dataset one-shot setting and 56.0% on five-shot segmentation, respectively. The code is available on the project website 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.14652")
get_code_for_paper("2303.14652")
have("2303.14652")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.14652.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.14652)
Connect an agent — have() is free.