Segmenter: Transformer for Semantic Segmentation by Robin Strudel, Ricardo Garcia, Ivan Laptev and Cordelia Schmid.
The code and several trained models will be released soon.
Segmentation maps of Seg-B-Mask/16 trained on ADE20K segmentation dataset and tested on DAVIS video dataset.
@article{strudel2021,
title={Segmenter: Transformer for Semantic Segmentation},
author={Strudel, Robin and Garcia, Ricardo and Laptev, Ivan and Schmid, Cordelia},
journal={arXiv preprint arXiv:?},
year={2021}
}
The Vision Transformer code is based on timm library and the semantic segmentation training and evaluation pipeline is using mmsegmentation.