prismformore/Multi-Task-Transformer：论文代码ICLR2023《任务提词器：空间通道多任务提示用于

项目介绍

prismformore/Multi-Task-Transformer 是一个托管在 GitHub 上的开源项目，主要使用 Python 编写，采用 MIT License 许可证，目前获得 327 个 Star、25 次 Fork。

仓库全名: prismformore/Multi-Task-Transformer

README 摘要

: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,…

完整内容见 GitHub 原始 README 或本页。

常见问题

Multi-Task-Transformer 用什么语言开发？

主要使用 Python 编写，采用 MIT License 许可证，目前有 327 个 Star。

Multi-Task-Transformer 可以免费商用吗？

如何获取 Multi-Task-Transformer 的源码？

可以直接克隆仓库：git clone https://github.com/prismformore/Multi-Task-Transformer.git，默认分支为 main；安装与运行步骤见仓库 README。

Multi-Task-Transformer 最近还在维护吗？

仓库最近一次更新为 2024年4月24日，当前有 10 个未关闭 Issue；Star 数为 327，可作为社区活跃度的参考。

关于

GitHub 原始描述（英文）

Code of ICLR2023 paper "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" and ECCV2022 paper "Inverted Pyramid Multi-task Transformer for Dense Scene Understanding"

cityscapes cityscapes-3d computer-vision deep-learning depth-estimation eccv2022 human-parsing multi-task-learning nyudv2 pascal scene-understanding segmentation

MIT License
327 Stars
25 Forks
5 Watching

描述取自 GitHub 官方 API，保持仓库作者书写的原文。

简要分析

热度分

382

价值分

203

活跃状态

活跃

GitHub

语言占比

C++

Cuda

Python

Shell

贡献者

prismformore

Python 3.7

: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

img-name

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

img-name

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.

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

暂无评论

Multi-Task-Transformer