{"id":25198072,"url":"https://github.com/khurramhashmi/featenhancer","last_synced_at":"2025-05-08T22:43:02.056Z","repository":{"id":249779119,"uuid":"803925253","full_name":"khurramHashmi/FeatEnHancer","owner":"khurramHashmi","description":"[ICCV 2023] FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision","archived":false,"fork":false,"pushed_at":"2024-08-19T08:13:16.000Z","size":4888,"stargazers_count":31,"open_issues_count":6,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-08T22:42:56.685Z","etag":null,"topics":["deep-learning","feature-enhancer","hierarchical-features","iccv2023","low-light-vision","object-detection","pytorch"],"latest_commit_sha":null,"homepage":"https://khurramhashmi.github.io/FeatEnHancer/","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/khurramHashmi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2024-05-21T16:10:09.000Z","updated_at":"2025-03-18T05:53:21.000Z","dependencies_parsed_at":"2025-02-10T02:40:50.199Z","dependency_job_id":"50f04f2a-98ed-4719-bc4c-7f98f541a732","html_url":"https://github.com/khurramHashmi/FeatEnHancer","commit_stats":null,"previous_names":["khurramhashmi/featenhancer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khurramHashmi%2FFeatEnHancer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khurramHashmi%2FFeatEnHancer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khurramHashmi%2FFeatEnHancer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/khurramHashmi%2FFeatEnHancer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/khurramHashmi","download_url":"https://codeload.github.com/khurramHashmi/FeatEnHancer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253160727,"owners_count":21863624,"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":["deep-learning","feature-enhancer","hierarchical-features","iccv2023","low-light-vision","object-detection","pytorch"],"created_at":"2025-02-10T02:40:43.554Z","updated_at":"2025-05-08T22:43:02.028Z","avatar_url":"https://github.com/khurramHashmi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Published Paper](https://img.shields.io/badge/Published-Paper-blue.svg)](https://openaccess.thecvf.com/content/ICCV2023/papers/Hashmi_FeatEnHancer_Enhancing_Hierarchical_Features_for_Object_Detection_and_Beyond_Under_ICCV_2023_paper.pdf)\n[![Supplementary Material](https://img.shields.io/badge/Supplementary-Material-green.svg)](https://openaccess.thecvf.com/content/ICCV2023/supplemental/Hashmi_FeatEnHancer_Enhancing_Hierarchical_ICCV_2023_supplemental.pdf)\n[![webpage](https://img.shields.io/badge/🖥-Website-9cf)](https://khurramhashmi.github.io/FeatEnHancer/)\n\n\n\n\n\n\u003ch1\u003e[ICCV 2023] FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision\u003c/h1\u003e\n\n-----\n### Enhancing representation of a low-light image.\n\u003cdiv align=\"center\"\u003e\n  \u003ctable\u003e\n      \u003ctd\u003e\n        \u003cimg src=\"docs/assets/enhanced_representation.gif\" height=\"800\"\u003e\n      \u003c/td\u003e\n  \u003c/table\u003e\n\u003c/div\u003e\n\n-----\n\n## Installation\n\nPlease refer to [low-light-object-detection-detectron2](https://github.com/khurramHashmi/FeatEnHancer/tree/main/low-light-object-detection-detectron2#readme) for installation requirements\n\n## Datasets\n\n### ExDark\n\nCreate a new folder named \"exdark\" in the \"low-light-object-detection-detectron2/data\" folder.\nCreate a new folder named \"exdark\" in the \"low-light-object-detection-mmdetection/data\" folder.\n\nDownload the [ExDark](https://github.com/cs-chan/Exclusively-Dark-Image-Dataset) dataset and copy the images into \"low-light-object-detection-detectron2/data/exdark/images/\" and \"low-light-object-detection-mmdetection/data/exdark/images/\" folders.\n\n\n### DARK FACE\n\nCreate a new folder named \"darkface\" in the \"low-light-object-detection-detectron2/data\" folder.\nCreate a new folder named \"darkface\" in the \"low-light-object-detection-mmdetection/data\" folder.\n\nDownload the [DARK FACE](https://flyywh.github.io/CVPRW2019LowLight/) dataset and copy the images into \"low-light-object-detection-detectron2/data/darkface/images/\" and \"low-light-object-detection-mmdetection/data/darkface/images/\" folders.\n\n\n\n## Train\n\nTo train the ExDark and DARK FACE using FeatEnHancer based Featurized Query R-CNN run the following commands:\nThe training utilizes 2 GPU's\n\n```\nsh low-light-object-detection-detectron2/train_exdark.sh\nsh low-light-object-detection-detectron2/train_darkface.sh\n```\n\nTo train the ExDark and DARK FACE using FeatEnHancer based RetinaNet run the following commands:\nThe training utilizes 6 GPU's\n\n```\nsh low-light-object-detection-mmdetection/exec_script_exdark.sh\nsh low-light-object-detection-mmdetection/exec_script_darkface.sh\n```\n\n\n## Results and Checkpoints\n\n### ExDark\n\n| Model                                 | mAP | Config |  \n|:--------------------------------------|  :---:  |:---:  |\n| FeatEnHancer + Featurized Query R-CNN | 86.3 | [config](low-light-object-detection-detectron2/configs/exdark_config.yaml) | \n### DARK FACE\n\n| Model    | mAP | Config | \n| :---     |  :---:  |:---:  |\n| FeatEnHancer + Featurized Query R-CNN | 69.0 | [config](low-light-object-detection-detectron2/configs/darkface_config.yaml) | \n\n\n\n### Reproducing Results on Other Downstream Vision Tasks:\n* The models developed for other downstream tasks, such as Semantic Segmentation and Video Object Detection, utilize distinct frameworks (MMDet, MMSeg, and MMTracking). Hence, it was not possible to release a unified repository at this time. However, to facilitate reproducibility of results, the same [FeatEnHancer script](low-light-object-detection-detectron2/queryrcnn/featenhancer/feat_enhancer.py) can be employed across these different tasks.\n\n\n\n## Acknowledgment\n\nThis work would not be possible without the following codebases. We gratefully thank the authors and collaborators for their wonderful works:  \n[Featurized Query R-CNN](https://github.com/hustvl/Featurized-QueryRCNN/), \n[detectron2](https://github.com/facebookresearch/detectron2),\n[mmdetection](https://github.com/open-mmlab/mmdetection/tree/2.x),\n[mmsegmentation](https://github.com/open-mmlab/mmsegmentation), and\n[mmtracking](https://github.com/open-mmlab/mmtracking/tree/1.x)\n\n\n## License\nThe proposed FeatEnHancer is released under the [Creative Commons Attribution-NonCommercial 4.0 International Licence](LICENSE).\n\n\n## Citation\n\nIf you find FeatEnHancer useful in your research or applications, please consider giving us a star :star: and citing it by the following BibTeX entry.\n\n```bibtex\n@InProceedings{FeatEnHancer_Hashmi_ICCV23,\n    author    = {Hashmi, Khurram Azeem and Kallempudi, Goutham and Stricker, Didier and Afzal, Muhammad Zeshan},\n    title     = {FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision},\n    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},\n    month     = {October},\n    year      = {2023},\n    pages     = {6725-6735}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkhurramhashmi%2Ffeatenhancer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkhurramhashmi%2Ffeatenhancer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkhurramhashmi%2Ffeatenhancer/lists"}