Invitation of incoporating LoveDA dataset into MMSegmentation.

[MengzhangLI]

Hi, I am member of OpenMMLab who develops MMSegmentation. Our vision is provide up-to-date methods and dataset(i.e., benchmark) for researchers and community around the world.

First, congrats for acceptance of NeurIPS'21. I think this dataset and benchmark would definitely help Remote Sensing Image field where semantic segmentation plays an important role.

Frankly speaking, right now we do not have too much human resources. Would you like to help us incpoorate your dataset into MMSegmentation? We appreciate all contibutors and users, here is our contributing details.

I think if LoveDA is provided by MMSegmentation, it could let more people use & cite this excellent work, especially for those who want to establish standard segmentation benchmark.

Looking forward to your reply. Wish you all the best.

Best,

[Junjue-Wang]

Thank you for your approval. I am willing to merge the LoveDA into MMSegmentation. Please tell me how to provide help.

[MengzhangLI]

Sorry for the late reply, because last week we were very busy.

I think we could first merge the dataset into MMSegmentation. Here are:

(1) Installation of MMSegmentation.
Please refer to get_started.md for installation and dataset_prepare.md for dataset preparation.

(2) Making a pull request.
Usefule links: Contributing to OpenMMLab and Chinese article from zhihu.

(3) Customization of LoveDA dataset.
Usefule links: doc of customized dataset and PR about supporting coco-stuff dataaset.

For LoveDA dataset, please refer to PR about supporting coco-stuff dataaset. It's a little bit laborious but that would make users more convenient after this treatment.

After that, we would train many models (for example, Swin Transformer, PSPNet and DeepLabV3, etc) to ensure LoveDA as a benchmark dataset in remote sensing image segmentation. That would be implemented on our computation resources.

If you have any problems about usage or pr of MMSegmentation, feel free to contact us. Let's work together to provide LoveDA as a benchmark for community!

Best,

[Junjue-Wang]

Thank you for your helpful reply. I will follow this step to integrate LoveDA into MMSegmentation :)

[MengzhangLI]

OK, maybe we could have a meeting next few weeks.

Feel free to call us if you have any problems.

Best,

[Junjue-Wang]

Okay, I will try to learn by myself at first.

[Junjue-Wang]

OK, maybe we could have a meeting next few weeks.

Feel free to call us if you have any problems.

Best,

I have already pulled a request on mmsegmentation, please see open-mmlab/mmsegmentation#1006 (comment).
Due to hardware limitations and not being familiar with this project, I haven't done any unit testing.
I would appreciate it if you can help me check the modifications : )