TESN: Transformers Enhanced Segmentation Network

Introduction

We proposed Transformers Enhanced Segmentation Network (TESN) which made the following improvements to the original Mask R-CNN to improve the accuracy of instance segmentation:
a) TESN adopt multi-stage architecture to provide high-quality target detection.
b) TESN Introduce Transformer into the mask head to provide high-quality segmentation.



The framework of the mask head. (a) mask head of original Mask R-CNN. (b) mask head of TESN. (c) convolution and up-sampling. (d) Transformer layer.


Results on MS COCO dataset :

Prepared to train

Environment

python 3.7.10
cuda 10.1
torch 1.5.0
mmcv-full 1.3.8
mmdet 2.18.0

File

1)Place Mask_transformer_head.py and transformers.py under ../mmdetection/mmdet/models/roi_heads/mask_heads
2)Place TESN_COCO.py under ../mmdetection
3)add 'from .Mask_transformer_head import FCNMaskTransformerHead' into ../mmdetection/mmdet/models/roi_heads/mask_heads/init.py

Train

Run 'python tools/train.py TESN.py'

Test

Run 'python tools/test.py TESN.py'

Acknowledgement

With greatly appreciation for open-mmlab for providing mmdetection source code.

Citation

If you find the code helpful in your resarch or work, please cite the following paper：

@article{WANG2022117673,
title = {TESN: Transformers enhanced segmentation network for accurate nanoparticle size measurement of TEM images},
author = {Zelin Wang and Li Fan and Yuxiang Lu and Jikai Mao and Lvtao Huang and Jianguang Zhou}，
journal = {Powder Technology},
volume = {407},
pages = {117673},
year = {2022},
issn = {0032-5910},
}