{"id":17141987,"url":"https://github.com/andrewekhalel/mtl_pan_seg","last_synced_at":"2025-04-13T10:40:40.818Z","repository":{"id":138422024,"uuid":"162285808","full_name":"andrewekhalel/MTL_PAN_SEG","owner":"andrewekhalel","description":"Implementation of \"Multi-task Deep Learning for Satellite Image Pansharpening and Segmentation\"","archived":false,"fork":false,"pushed_at":"2018-12-18T13:20:27.000Z","size":57892,"stargazers_count":21,"open_issues_count":0,"forks_count":10,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-27T02:02:58.865Z","etag":null,"topics":["multi-task-learning","pansharpening","satellite-imagery","segmentation","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/andrewekhalel.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"license.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-12-18T12:34:42.000Z","updated_at":"2024-01-14T03:40:04.000Z","dependencies_parsed_at":"2023-09-22T07:25:04.450Z","dependency_job_id":null,"html_url":"https://github.com/andrewekhalel/MTL_PAN_SEG","commit_stats":{"total_commits":5,"total_committers":1,"mean_commits":5.0,"dds":0.0,"last_synced_commit":"0b227d56039e9914faf533e875c64400c4d046f2"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewekhalel%2FMTL_PAN_SEG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewekhalel%2FMTL_PAN_SEG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewekhalel%2FMTL_PAN_SEG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewekhalel%2FMTL_PAN_SEG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andrewekhalel","download_url":"https://codeload.github.com/andrewekhalel/MTL_PAN_SEG/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248700946,"owners_count":21147938,"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":["multi-task-learning","pansharpening","satellite-imagery","segmentation","tensorflow"],"created_at":"2024-10-14T20:29:35.675Z","updated_at":"2025-04-13T10:40:40.795Z","avatar_url":"https://github.com/andrewekhalel.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Implementation of the methods described in the paper entitled “Multi-task deep learning for satellite image pansharpening and segmentation”\n\n### Multi-task Framework Architecture\n![Framework](https://raw.githubusercontent.com/andrewekhalel/MTL_PAN_SEG/master/docs/figures/framework.png)\n\n### Software Architecture\n![Software Architecture](https://raw.githubusercontent.com/andrewekhalel/MTL_PAN_SEG/master/docs/figures/software_architecture.png)\n\n### Dependencies\n\n - Python 3.6.4\n - Tensorflow 1.10.0\n - Numpy 1.14.2\n - GDAL 2.2.4  \nThe codes have been tested on Fedora 25\n\n#### Visualization (Optional)\nWe recommend to use [QGIS](https://qgis.org/en/site/), where the outputs can easily be displayed despite of the image size.\n\n### Usage\n\n - The solver sub-directories, namely training_solvers and test_solvers contain solvers, which train a model and test the trained model (See the figure under Software Architecture section).\n - To train a model, enter the following command (we assume that you are under multi-task directory, otherwise you will get an error): `python3 train_solvers/train_solver\u003cid\u003e.py`\n - To test a trained model, enter this command: `python3 test_solvers/test_solver\u003cid\u003e.py`  \n  \n`\u003cid\u003e` in the commands above determines which solver to run.\n\n### Example Visual Results From the World-View3 Dataset\nHere, we illustrate several original visual outputs from the World-View3 dataset for different methods including our multi-task framework.\n\n![Results](https://raw.githubusercontent.com/andrewekhalel/MTL_PAN_SEG/master/docs/figures/results.png)\n\n### Citation\n```\n@inproceedings{khalel2019multi,\n  title={Multi-task deep learning for satellite image pansharpening and segmentation},\n  author={Khalel, Andrew and Tasar, Onur and Charpiat, Guillaume and Tarabalka, Yuliya},\n  booktitle={IEEE International Geoscience and Remote Sensing Symposium--IGARSS 2019},\n  year={2019}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrewekhalel%2Fmtl_pan_seg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandrewekhalel%2Fmtl_pan_seg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrewekhalel%2Fmtl_pan_seg/lists"}