hugozanini / segformer-clothes-tfjs

Clothes semantic segmentation with Transformers

Real-time clothes segmentation with TF.JS

Real-time implementation of the SegFormer model fine-tuned on ATR dataset for clothes segmentation

SegFormer is a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders. [Paper]

The model recognizes 17 different classes and just need a webpage to run.

Citation

@article{DBLP:journals/corr/abs-2105-15203,
  author    = {Enze Xie and
               Wenhai Wang and
               Zhiding Yu and
               Anima Anandkumar and
               Jose M. Alvarez and
               Ping Luo},
  title     = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
               Transformers},
  journal   = {CoRR},
  volume    = {abs/2105.15203},
  year      = {2021},
  url       = {https://arxiv.org/abs/2105.15203},
  eprinttype = {arXiv},
  eprint    = {2105.15203},
  timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Acknowledgment

This code was developed under the financial assistance of the Google Developers Group, which provided all the computational resources for training and converting the models.