{"id":13738244,"url":"https://github.com/Junjue-Wang/LoveDA","last_synced_at":"2025-05-08T16:32:57.027Z","repository":{"id":38532987,"uuid":"416590697","full_name":"Junjue-Wang/LoveDA","owner":"Junjue-Wang","description":"[NeurIPS 2021] LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation","archived":false,"fork":false,"pushed_at":"2024-12-02T10:35:29.000Z","size":119,"stargazers_count":363,"open_issues_count":39,"forks_count":50,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-12-02T11:37:25.757Z","etag":null,"topics":["domain-adaptation","pytorch","remote-sensing","semantic-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Junjue-Wang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-10-13T04:39:02.000Z","updated_at":"2024-12-02T10:35:33.000Z","dependencies_parsed_at":"2023-01-23T22:02:11.339Z","dependency_job_id":"68cf8c6f-0246-4c95-adf7-61db963b5307","html_url":"https://github.com/Junjue-Wang/LoveDA","commit_stats":{"total_commits":68,"total_committers":3,"mean_commits":"22.666666666666668","dds":0.5,"last_synced_commit":"6366cbaed617574435351622b81d18e420cf201e"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Junjue-Wang%2FLoveDA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Junjue-Wang%2FLoveDA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Junjue-Wang%2FLoveDA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Junjue-Wang%2FLoveDA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Junjue-Wang","download_url":"https://codeload.github.com/Junjue-Wang/LoveDA/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253105397,"owners_count":21855019,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["domain-adaptation","pytorch","remote-sensing","semantic-segmentation"],"created_at":"2024-08-03T03:02:15.603Z","updated_at":"2025-05-08T16:32:57.005Z","avatar_url":"https://github.com/Junjue-Wang.png","language":"Python","funding_links":[],"categories":["Python","Architecture families and real-time models"],"sub_categories":["Specialized directions"],"readme":"\u003ch2 align=\"center\"\u003eLoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation\u003c/h2\u003e\n\n\u003ch5 align=\"right\"\u003eby \u003ca href=\"https://junjue-wang.github.io/homepage/\"\u003eJunjue Wang\u003c/a\u003e, \u003ca href=\"http://zhuozheng.top/\"\u003eZhuo Zheng\u003c/a\u003e, Ailong Ma, Xiaoyan Lu, and \u003ca href=\"http://rsidea.whu.edu.cn/\"\u003eYanfei Zhong\u003c/a\u003e\u003c/h5\u003e\n\n[[`Paper`](https://www.researchgate.net/profile/Junjue-Wang/publication/355390292_LoveDA_A_Remote_Sensing_Land-Cover_Dataset_for_Domain_Adaptive_Semantic_Segmentation/links/617cd8bda767a03c14cecbc9/LoveDA-A-Remote-Sensing-Land-Cover-Dataset-for-Domain-Adaptive-Semantic-Segmentation.pdf?_sg%5B0%5D=Iw5FPui1-9iYrZN7aZO766hZA-LmublHlq8bp0694vUeIGDIzp5SGTfYN-OWhurZOujSPU0RDZ5lW0i02HVUew.7x9qdrvJwRmAnsqEyh5-xSFdh0M9AaTpdXcZCfHyhVl5GNLR5nlDIx8ctTXFy1HE1yNexX4ytzYqJWkAGJVTvg.Rrg3rXhcp9mMlLTU3n9Jf-h0Kt8VzHAd0AmhG2yPQxI-yRK6J0wAulUZ65dih6BQ9CbrQm0_23_nULO_BXwaJg\u0026_sg%5B1%5D=KLu7pn0g50f8FwKE9x5iOuDPYb8VaOpX4k_ieq8eWJVVeJyXbZJO-O4pCL687QRxYbBnWdo7fJj8FZEOc3t3lgVVyDz0CFS-ff7LToXj4R9W.7x9qdrvJwRmAnsqEyh5-xSFdh0M9AaTpdXcZCfHyhVl5GNLR5nlDIx8ctTXFy1HE1yNexX4ytzYqJWkAGJVTvg.Rrg3rXhcp9mMlLTU3n9Jf-h0Kt8VzHAd0AmhG2yPQxI-yRK6J0wAulUZ65dih6BQ9CbrQm0_23_nULO_BXwaJg\u0026_iepl=)],\n[[`Video`](https://slideslive.com/38969542)],\n[[`Dataset`](https://doi.org/10.5281/zenodo.5706578)],\n[[`BibTeX`](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/file/4e732ced3463d06de0ca9a15b6153677-Bibtex-round2.bib)],\n[[`Leaderboard-SEG`](https://codalab.lisn.upsaclay.fr/competitions/421)],\n[[`Leaderboard-UDA`](https://codalab.lisn.upsaclay.fr/competitions/424)]\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/Junjue-Wang/resources/blob/main/LoveDA/LoveDA.jpg?raw=true\"\u003e\n  \u003cimg src=\"https://github.com/Junjue-Wang/resources/blob/main/LoveDA/statics_diff.png?raw=true\"\u003e\n\u003c/div\u003e\n\n## News\n- 2024/05/12, The new version of LoveDA dataset has been released at [\u003cb\u003eEarthVQA\u003c/b\u003e](https://github.com/Junjue-Wang/EarthVQA) dataset.\n\n- 2021/12/13, Pre-trained urls for HRNet have been updated.\n\n- 2021/12/10, LoveDA has been included in\n[\u003cb\u003eTorchgeo\u003c/b\u003e](https://github.com/microsoft/torchgeo/blob/main/torchgeo/datasets/loveda.py).\n\n- 2021/11/30, The contests have been moved to new server:\n[\u003cb\u003eLoveDA Semantic Segmentation Challenge\u003c/b\u003e](https://codalab.lisn.upsaclay.fr/competitions/421), [\u003cb\u003eLoveDA Unsupervised Domain Adaptation Challenge\u003c/b\u003e](https://codalab.lisn.upsaclay.fr/competitions/424).\n\n- 2021/11/11, LoveDA has been included in [MMsegmentation](https://github.com/open-mmlab/mmsegmentation).\n🔥🔥 The Semantic Segmentation task can be prepared follow [dataset_prepare.md](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/dataset_prepare.md#loveda).🔥🔥 \n\n\n\n\n## Highlights\n1. 5987 high spatial resolution (0.3 m) remote sensing images from Nanjing, Changzhou, and Wuhan\n2. Focus on different geographical environments between Urban and Rural\n3. Advance both semantic segmentation and domain adaptation tasks\n4. Three considerable challenges:\n    * Multi-scale objects\n    * Complex background samples\n    * Inconsistent class distributions\n\n## Citation\nIf you use LoveDA in your research, please cite our NeurIPS2021 paper.\n```text\n    @inproceedings{NEURIPS DATASETS AND BENCHMARKS2021_4e732ced,\n         author = {Wang, Junjue and Zheng, Zhuo and Ma, Ailong and Lu, Xiaoyan and Zhong, Yanfei},\n         booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks},\n         editor = {J. Vanschoren and S. Yeung},\n         pages = {},\n         publisher = {Curran Associates, Inc.},\n         title = {LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation},\n         url = {https://datasets-benchmarks-proceedings.neurips.cc/paper_files/paper/2021/file/4e732ced3463d06de0ca9a15b6153677-Paper-round2.pdf},\n         volume = {1},\n         year = {2021}\n    }\n    @dataset{junjue_wang_2021_5706578,\n        author={Junjue Wang and Zhuo Zheng and Ailong Ma and Xiaoyan Lu and Yanfei Zhong},\n        title={Love{DA}: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation},\n        month=oct,\n        year=2021,\n        publisher={Zenodo},\n        doi={10.5281/zenodo.5706578},\n        url={https://doi.org/10.5281/zenodo.5706578}\n    }\n```\n\n\n## Dataset and Contest\nThe LoveDA dataset is released at [\u003cb\u003eZenodo\u003c/b\u003e](https://doi.org/10.5281/zenodo.5706578)\nand [\u003cb\u003eBaidu Drive\u003c/b\u003e](https://pan.baidu.com/s/1YrU1Y4Y0dS0f_OOHXpzspQ) Code: 27vc\n\n\n\nYou can develop your models on Train and Validation sets.\n\nCategory labels: background – 1, building – 2, road – 3,\n                 water – 4, barren – 5,forest – 6, agriculture – 7. And the no-data regions were assigned 0\n                 which should be ignored. The provided data loader will help you construct your pipeline.  \n                 \n\nSubmit your test results on [\u003cb\u003eLoveDA Semantic Segmentation Challenge\u003c/b\u003e](https://codalab.lisn.upsaclay.fr/competitions/421), [\u003cb\u003eLoveDA Unsupervised Domain Adaptation Challenge\u003c/b\u003e](https://codalab.lisn.upsaclay.fr/competitions/424).\nYou will get your Test scores smoothly.\n\nFeel free to design your own models, and we are looking forward to your exciting results!\n\n\n## License\nThe owners of the data and of the copyright on the data are [RSIDEA](http://rsidea.whu.edu.cn/), Wuhan University.\nUse of the Google Earth images must respect the [\"Google Earth\" terms of use](https://about.google/brand-resource-center/products-and-services/geo-guidelines/).\nAll images and their associated annotations in LoveDA can be used for academic purposes only,\n\u003cfont color=\"red\"\u003e\u003cb\u003e but any commercial use is prohibited.\u003c/b\u003e\u003c/font\u003e\n\n\u003ca rel=\"license\" href=\"https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en\"\u003e\n\u003cimg alt=\"知识共享许可协议\" style=\"border-width:0\" src=\"https://i.creativecommons.org/l/by-nc-sa/4.0/88x31.png\" /\u003e\u003c/a\u003e\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=Junjue-Wang/LoveDA\u0026type=Date)](https://star-history.com/#Junjue-Wang/LoveDA\u0026Date)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FJunjue-Wang%2FLoveDA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FJunjue-Wang%2FLoveDA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FJunjue-Wang%2FLoveDA/lists"}