bobrown / segnet_source

The code of source-only training for our method

Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation

[paper] IEEE Link

[paper] ArXiv Link

If you find our code or paper useful to your research work, please consider citing our work using the following bibtex:

@article{zhang2021curriculum,
  title={Curriculum-Style Local-to-Global Adaptation for Cross-Domain Remote Sensing Image Segmentation},
  author={Zhang, Bo and Chen, Tao and Wang, Bin},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  volume={60},
  pages={1--12},
  year={2021},
  publisher={IEEE}
}

Preprocessing data

Following DualGAN, we crop the whole images in Potsdam IR-R-G dataset into the size of 512 × 512 with both horizontal and vertical strides of 512 pixels, and generate 4598 patches. For Vaihingen dataset, we crop the whole images into a size of 512 × 512 with both horizontal and vertical strides of 256 pixels and obtain 1696 patches

The following processed datasets are used in our paper:

• PotsdamIRRG [Dataset Page]
• PotsdamRGB [Dataset Page]
• Vaihingen [Dataset Page]

After dowloading datasets, copy the data.zip to /ADVENT/. and extract it:

unzip data.zip

Dowloading the ImageNet pretrained model

• ImageNet pretrained weights [Dataset Page]

Train the source-only model from ImageNet pretrained model

cd /SegNet_Source/ADVENT/.
pip install -e .
cd /SegNet_Source/ADVENT/scripts/.
python train.py --cfg /root/code/SegNet_Source/ADVENT/advent/scripts/configs/advent.yml

Test the source-only model

python test.py --cfg /root/code/SegNet_Source/ADVENT/advent/scripts/configs/advent.yml

Contact

We have tried our best to verify the correctness of our released data, code and trained model weights. However, there are a large number of experiment settings, all of which have been extracted and reorganized from our original codebase. There may be some undetected bugs or errors in the current release. If you encounter any issues or have questions about using this code, please feel free to contact us via [email protected]

segnet_source's Issues

代码训练的问题

老师，您好。我的数据集是二分类，在训练纯源域模型后进行测试时，发现背景IoU为0，这是为什么呢？要怎么进行调整？
以下是部分测试结果：
Evaluating model E:\root\code\Source_main\ADVENT\experiments\snapshots\deeplab_v3_PotsdamIRRG_source\model_2000.pth
20%|█▉ | 100/510 [00:09<00:31, 12.89it/s]100 / 510: 37.78
39%|███▉ | 200/510 [00:17<00:25, 12.26it/s]200 / 510: 38.44
59%|█████▉ | 300/510 [00:25<00:17, 12.04it/s]300 / 510: 37.87
78%|███████▊ | 400/510 [00:34<00:08, 12.44it/s]400 / 510: 39.07
98%|█████████▊| 501/510 [00:44<00:00, 12.59it/s]500 / 510: 40.14
100%|██████████| 510/510 [00:45<00:00, 11.22it/s]
Current mIoU: 39.97
Current best model: E:\root\code\Source_main\ADVENT\experiments\snapshots\deeplab_v3_PotsdamIRRG_source\model_2000.pth
Current best mIoU: 39.97
oil 79.94
background 0.0

关于代码训练问题

您好，我好像没在您代码里看到具体怎么训练的。请问这个代码怎么用呀。source-only和自适应的训练代码不应该一样吧