:fire: [ICLR2023, ECCV2022, TPAMI2024] Powerful Multi-Task Transformers for Scene Understanding

:scroll: Introduction

This repository provides codes and models for two powerful multi-task transformer models for scene understanding. Please check the following pages for details:

Hanrong Ye and Dan Xu, TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding. ICLR 2023

Hanrong Ye and Dan Xu, Inverted Pyramid Multi-task Transformer for Dense Scene Understanding. ECCV 2022

Cite

BibTex:

@InProceedings{invpt2022,
  title={Inverted Pyramid Multi-task Transformer for Dense Scene Understanding},
  author={Ye, Hanrong and Xu, Dan},
  booktitle={ECCV},
  year={2022}
}
@InProceedings{taskprompter2023,
  title={TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding},
  author={Ye, Hanrong and Xu, Dan},
  booktitle={ICLR},
  year={2023}
}
@article{ye2023invpt++,
  title={InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding},
  author={Ye, Hanrong and Xu, Dan},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2024}
}

Please do consider :star2: star our project to share with your community if you find this repository helpful!

Contact

Please contact Hanrong Ye if any questions.

Related Project

Few-show learning of multiple tasks: Visual Token Matching (ICLR 2023 Outstanding Paper Award)