Roadmap of MMSegmentation

[csatsurnh]

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.

You can either:

1. Suggest a new feature by leaving a comment.
2. Vote for a feature request with +1 or be against with -1. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
3. Tell us that you would like to help implement one of the features in the list or review the PRs. (This is the greatest things to hear about!)

V0.1.0(2023.3)

• code

Task	Description	Difficulty	Status
Support Hausdorff distance loss	Realize Hausdorff distance loss refer to the source code	★★☆	❤️ Picked! #2820 Thanks to @jinxianwei
Support boundary loss	Realize boundary loss refer to the source code	★★☆	❤️ Picked! Thanks to @Fun772283153
Support SwinV2 (UperNet) model	Add SwinV2 (UperNet) model in MMSegmentation projects, inference accuracy needed to align with the original open source code library, details see	★★★	🤍 Pick me!
Support TransUnet model	Add TransUnet model in MMSegmentation projects, inference accuracy needed to align with the original open source code library, details see	★★★	🤍 Pick me!
Add semantic information to segmentation results visualization	Current segmentation result visualization only assign a specified color to each semantic segmentation area without category information, the task is to add segmentation category information to the visualization results, details see	★★☆	❤️ Picked! Thanks to @JoyMei

Task	Description	Difficulty	Status
支持 Hausdorff distance loss	参考源码地址实现 Hausdorff distance loss	★★☆	❤️ Picked! #2820 Thanks to @jinxianwei
支持 boundary loss	参考源码地址实现 boundary loss	★★☆	❤️ Picked! Thanks to @Fun772283153
支持 SwinV2 (UperNet) 模型	在 MMSegmentation projects 中添加 SwinV2 (UperNet) 模型，需要和原始开源代码库中的模型推理精度一致，详细可见	★★★	🤍 Pick me!
支持 TransUnet 模型	在 MMSegmentation projects 中添加 TransUnet 模型，需要和原始开源代码库中的模型推理精度一致，详细可见	★★★	🤍 Pick me!
分割可视化结果中加上语义信息	当前分割结果可视化内容是只是给每一个语义分割区域分配指定颜色，没有类别信息，该任务是希望将分割类别信息添加到可视化结果中，详细可见	★★☆	❤️ Picked! Thanks to @JoyMei

• documentation

Task	Description	Difficulty	Status
Zh_CN FAQ documentation migration	Migrate several common usage questions in MMSegmentation master branch Chinese FAQ documentation to dev-1.x branch Chinese FAQ documentation	★☆☆	❤️ #2769 Thanks to @AI-Tianlong
EN FAQ documentation migration	Migrate several common usage questions in MMSegmentation master branch English FAQ documentation to dev-1.x branch English FAQ documentation	★☆☆	❤️ #2765 Thanks to @Renzhihan

Task	Description	Difficulty	Status
中文 FAQ 文档迁移	MMSegmentation master 分支 FAQ 中文文档中有多个常见使用问题迁移到 dev-1.x 分支 FAQ 中文文档中	★☆☆	❤️ #2769 Thanks to @AI-Tianlong
英文 FAQ 文档迁移	MMSegmentation master 分支 FAQ 英文文档中有多个常见使用问题迁移到 dev-1.x 分支 FAQ 英文文档中	★☆☆	❤️ #2765 Thanks to @Renzhihan

[jediofgever]

Can you support segfromer in mmdeploy, this network performance very well to my case but the inference time is quite slow.

[xiexinch]

2023.04 Development plan

• Merge part of medical image datasets pull requests
• Support data loading of remote sensing images [Feature] Add GDAL backend and Support LEVIR-CD Dataset #2903
• Support DDRNet in main dev-1.x branch [Feature] Support DDRNet #2855
• ...

To develop a better segmentation toolbox for everyone. Welcome any contributions and suggestions🙏.