Home

Awesome

A Transformer-based Decoder for Semantic Segmentation with Multi-level Context Mining

Official implementation of the paper "A Transformer-based Decoder for Semantic Segmentation with Multi-level Context Mining",

by Bowen Shi*, Dongsheng Jiang*, Xiaopeng Zhang, Han Li, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian.

[Paper] [Appendix]

<div align="center"> <img src="./imgs/framework.png" alt="framework" align=center /> </div>

Installation

Our code is based on MMSegmentation. For install and data preparation, please refer to the guidelines in MMSegmentation.

Training

Example: train SegFormer-B1 + SegDeformer on ADE20K:

python start_local_train.py --config_file segformer/segformer_mit-b1_512x512_160k_ade20k_segdeformer3.py

Results

ADE20K

MethodBackboneCrop SizeLr schdmIoUconfiglog
SegFormer-B1MiT-B1512x51216000040.97--
SegFormer-B1 + SegDeformerMiT-B1512x51216000044.12configlog
SegFormer-B2MiT-B2512x51216000045.58--
SegFormer-B2 + SegDeformerMiT-B2512x51216000047.34configlog
SegFormer-B5MiT-B5512x51216000049.13--
SegFormer-B5 + SegDeformerMiT-B5512x51216000050.34configlog

Note:

Acknowledgement

This reposity is based on the MMSegmentation repository. Thanks for their contributions to the community.

Citation

If you find this repository/work helpful in your research, welcome to cite the paper.

@inproceedings{shi2022transformer,
  title={A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining},
  author={Shi, Bowen and Jiang, Dongsheng and Zhang, Xiaopeng and Li, Han and Dai, Wenrui and Zou, Junni and Xiong, Hongkai and Tian, Qi},
  booktitle={European Conference on Computer Vision},
  pages={624--639},
  year={2022},
  organization={Springer}
}