Attribute-Cooperated-Classification-Datasets

Contents

Three Attribute-Cooperated-Classification-Datasets (ACC Datasets) are built based on three existing classficiation datasets:

• AC-AID based on AID [1] and RSICD [4]

• AC-UCM based on UCM [2] and Caption [5]

• AC-Sydney based on Sydney [3] and Caption [5]

Data sets overview

• AC-AID: 83 attribute items, 30 scene categories, 10000 images.

• AC-UCM: 56 attribute items, 21 scene categories, 2100 images.

• AC-Sydney: 30 attribute items, 7 scene categories, 613 images.

Attribute/Scene Lists for ACC Datasets

The attribute type list in here, where two columns are used to show attribute items and the sample counts of these attribute items.

The scene type list please refer to [1~3].

Citation

If you find the ACC Datasets usesful, please cite the following article.

@article{zhang2020Attribute,
  title={Attribute-Cooperated Convolutional Neural Network for Remote Sensing Image Classification},
  author={ Zhang, Yuanlin  and  Zheng, Xiangtao  and  Yuan, Yuan  and  Lu, Xiaoqiang },
  journal={IEEE Transactions on Geoence and Remote Sensing},
  volume={58},
  number={12},
  pages={8358-8371},
  year={2020}
  publisher={IEEE}
}

References

• [1] AID:

@article{xia2017aid,
	title={AID: A benchmark data set for performance evaluation of aerial scene classification},
	author={Xia, Gui-Song and Hu, Jingwen and Hu, Fan and Shi, Baoguang and Bai, Xiang and Zhong, Yanfei and Zhang, Liangpei and Lu, Xiaoqiang},
	journal={IEEE Transactions on Geoscience and Remote Sensing},
	volume={55},
	number={7},
	pages={3965--3981},
	year={2017},
	publisher={IEEE}
}

• [2] UCM:

@inproceedings{yang2010bag,
	title={Bag-of-visual-words and spatial extensions for land-use classification},
	author={Yang, Yi and Newsam, Shawn},
	booktitle={Proceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems},
	pages={270--279},
	year={2010},
	organization={ACM}
}

• [3] Sydney:

@article{zhang2014saliency,
	title={Saliency-guided unsupervised feature learning for scene classification},
	author={Zhang, Fan and Du, Bo and Zhang, Liangpei},
	journal={IEEE transactions on Geoscience and Remote Sensing},
	volume={53},
	number={4},
	pages={2175--2184},
	year={2014},
	publisher={IEEE}
}

• [4] RSICD:

@article{lu2017exploring,
	title={Exploring Models and Data for Remote Sensing Image Caption Generation},
	author={Lu, Xiaoqiang and Wang, Binqiang and Zheng, Xiangtao and Li, Xuelong},
	journal={IEEE Transactions on Geoscience and Remote Sensing},
	volume = {56},
	number = {4},
	pages = {2183-2195},
	year={2017},
	doi={10.1109/TGRS.2017.2776321}
}

• [5] Caption (ACM-caption , Sydney-caption):

@inproceedings{qu2016deep,
	title={Deep semantic understanding of high resolution remote sensing image},
	author={Qu, Bo and Li, Xuelong and Tao, Dacheng and Lu, Xiaoqiang},
	booktitle={2016 International Conference on Computer, Information and Telecommunication Systems (CITS)},
	pages={1--5},
	year={2016},
	organization={IEEE}
}