{"id":14112420,"url":"https://github.com/lichen14/awesome-weakly-supervised-segmentation","last_synced_at":"2025-08-01T14:33:38.710Z","repository":{"id":178193773,"uuid":"537269886","full_name":"lichen14/awesome-weakly-supervised-segmentation","owner":"lichen14","description":"Weakly Supervised Learning for Image Segmentation, a collection of literature reviews and code implementations.","archived":false,"fork":false,"pushed_at":"2022-10-27T02:35:57.000Z","size":2616,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-05-20T23:23:16.608Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lichen14.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}},"created_at":"2022-09-16T01:55:43.000Z","updated_at":"2024-02-03T21:59:28.000Z","dependencies_parsed_at":"2024-02-02T20:45:25.609Z","dependency_job_id":null,"html_url":"https://github.com/lichen14/awesome-weakly-supervised-segmentation","commit_stats":null,"previous_names":["lichen14/awesome-weakly-supervised-segmentation"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lichen14%2Fawesome-weakly-supervised-segmentation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lichen14%2Fawesome-weakly-supervised-segmentation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lichen14%2Fawesome-weakly-supervised-segmentation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lichen14%2Fawesome-weakly-supervised-segmentation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lichen14","download_url":"https://codeload.github.com/lichen14/awesome-weakly-supervised-segmentation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228389058,"owners_count":17912184,"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":[],"created_at":"2024-08-14T10:03:45.792Z","updated_at":"2024-12-05T23:31:04.650Z","avatar_url":"https://github.com/lichen14.png","language":null,"funding_links":[],"categories":["Other Lists"],"sub_categories":["TeX Lists"],"readme":"# Weakly-supervised-learning-for-image-analysis\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)  ![GitHub stars](https://img.shields.io/github/stars/lichen14/awesome-weakly-supervised-segmentation?color=yellow)  ![GitHub forks](https://img.shields.io/github/forks/lichen14/awesome-weakly-supervised-segmentation?color=green\u0026label=Fork)  ![visitors](https://visitor-badge.glitch.me/badge?page_id=lichen14.awesome-weakly-supervised-segmentation)\n* Recently, weak-supervised image analysis has become a hot topic in medical\u0026natural image computing. Unfortunately, there are only a few open-source codes and datasets, since the privacy policy and others. For easy evaluation and fair comparison, we are trying to build a weak-supervised image analysis benchmark to boost the weak-supervised learning research in the image computing community. \n* If you are interested, you can push your implementations or ideas to this repo or contact [me](https://lichen14.github.io/) at any time.\n* My personal interest is mainly focused on medical image segmentation tasks, but this repo will also collect many papers on natural image detection and segmentation tasks.   \n### Typical weak annotations include image-level labels, bounding boxes, points, and scribbles. This repo focus on points and scribbles.\n\n## Content\n- [Literature List](#literature-list)\n- [Benchmark](#benchmark)\n  * [Medical Images](#medical-images)\n    + [VS \u0026 BraTS](#brain-tumor-segmentation)\n    + [COVID-19](#is-covid-dataset)\n    + [ACDC](#acdc-dataset)\n    + [MSCMRseg](#mscmrseg-dataset)\n    + [LVSC](#lvsc-dataset)\n    + [CHAOS](#chaos-dataset)\n  * [Natural Images](#natural-images)\n    + [COD10K,CAMO,CHAMELEON](#camouflaged-object-detection)\n    + [DUTS testing dataset, ECSSD, DUT, PASCAL-S, HKU-IS, THUR](#salient-object-detection)\n    + [MS-COCO, PASCAL VOC , Bees, CrowdHuman and Objects365](#semi-or-weak-supervised-object-detection)\n  * [Others](#others)\n- [Tutorial](#tutorial)\n  * [中文](#中文)\n  * [English](#english)\n- [Conclusion](#conclusion)\n- [Questions and Suggestions](#questions-and-suggestions)\n\u003c!-- * This repo has re-implemented these semi-supervised methods (with some modifications for semi-supervised medical image segmentation, more details please refer to these original works): (1) [Mean Teacher](https://papers.nips.cc/paper/6719-mean-teachers-are-better-role-models-weight-averaged-consistency-targets-improve-semi-supervised-deep-learning-results.pdf); (2) [Entropy Minimization](https://openaccess.thecvf.com/content_CVPR_2019/papers/Vu_ADVENT_Adversarial_Entropy_Minimization_for_Domain_Adaptation_in_Semantic_Segmentation_CVPR_2019_paper.pdf); (3) [Deep Adversarial Networks](https://link.springer.com/chapter/10.1007/978-3-319-66179-7_47); (4) [Uncertainty Aware Mean Teacher](https://arxiv.org/pdf/1907.07034.pdf); (5) [Interpolation Consistency Training](https://arxiv.org/pdf/1903.03825.pdf); (6) [Uncertainty Rectified Pyramid Consistency](https://arxiv.org/pdf/2012.07042.pdf); (7) [Cross Pseudo Supervision](https://arxiv.org/abs/2106.01226); (8) [Cross Consistency Training](https://openaccess.thecvf.com/content_CVPR_2020/papers/Ouali_Semi-Supervised_Semantic_Segmentation_With_Cross-Consistency_Training_CVPR_2020_paper.pdf); (9) [Deep Co-Training](https://openaccess.thecvf.com/content_ECCV_2018/papers/Siyuan_Qiao_Deep_Co-Training_for_ECCV_2018_paper.pdf); (10) [Cross Teaching between CNN and Transformer](https://arxiv.org/pdf/2112.04894.pdf); (11) [FixMatch](https://arxiv.org/abs/2001.07685); (12) [Regularized Dropout](https://proceedings.neurips.cc/paper/2021/file/5a66b9200f29ac3fa0ae244cc2a51b39-Paper.pdf). In addition, several backbones networks (both 2D and 3D) are also supported in this repo, such as **UNet, nnUNet, VNet, AttentionUNet, ENet, Swin-UNet, etc**.\n\n* This project was initially developed for our previous works. Now and future, we are still working on extending it to be more user-friendly and support more approaches to boost further and ease this topic research. \n\u003ch1\u003e  --\u003e\n\n\n\u003c/h1\u003e\n\n## Literature List\n\u003ch3\u003e Keywords \u003c/h3\u003e\n\n__`scrib.`__: scribble level label \u0026emsp;|\u0026emsp; __`point.`__: point level label \u0026emsp; | __`box.`__: bounding box label \u0026emsp; | __`img.`__: image level label \u0026emsp; | \u0026emsp;\n\nStatistics: :fire: code is available \u0026 stars \u003e= 100 \u0026emsp;|\u0026emsp; :star: popular \u0026 cited in a survey \u0026emsp;|\u0026emsp;\n:sunflower: natural scene images \u0026emsp;|\u0026emsp; :earth_americas: remote sensing images \u0026emsp;|\u0026emsp; :hospital: medical images \n\n|Date|1st Institute|Title|Code|Publication|Label|Dataset|\n|---|---|---|---|---|---|---|\n|2022-08|University of Electronic Science and Technology of China 成电王国泰组|PA-Seg: Learning from Point Annotations for 3D Medical Image Segmen- tation using Contextual Regularization and Cross Knowledge Distillation|None|[Arxiv](https://arxiv.org/abs/2208.05669) under TMI revision|__`point.`__ |:hospital: [VS, BraTS](#vs)|\n|2022-07|City University of Hong Kong|Weakly-Supervised Camouflaged Object Detection with Scribble Annotation|None|[Arxiv](https://arxiv.org/abs/2207.14083)|__`scrib.`__ |:sunflower: [COD10K, CAMO, CHAMELEON](#camouflaged-object-detection)|\n|2022-06|Fudan University|CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision|[github](https://github.com/BWGZK/CycleMix)|[CVPR 2022](https://openaccess.thecvf.com/content/CVPR2022/html/Zhang_CycleMix_A_Holistic_Strategy_for_Medical_Image_Segmentation_From_Scribble_CVPR_2022_paper.html)|__`scrib.`__ |:hospital: [ACDC, MSCMRseg](#heart-segmentation)|\n|2022-03|Shanghai Jiao Tong University|Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations|[github](https://github.com/Qybc/Scribble2D5)|[MICCAI 2022](https://arxiv.org/abs/2205.06779v2)|__`scrib.`__ |:hospital: [ACDC, VS, CHAOS](#heart-segmentation)|\n|2022-03|University of Electronic Science and Technology of China 成电王国泰组|Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervision|[github](https://github.com/HiLab-git/WSL4MIS)|[MICCAI 2022](https://arxiv.org/abs/2203.02106v1)|__`scrib.`__ |:hospital: [ACDC](#heart-segmentation)|\n|2022-06|AWS AI Labs|Omni-DETR: Omni-Supervised Object Detection with Transformers|[github](https://github.com/amazon-research/omni-detr)|[CVPR 2022](https://openaccess.thecvf.com/content/CVPR2022/html/Wang_Omni-DETR_Omni-Supervised_Object_Detection_With_Transformers_CVPR_2022_paper.html)|__`point.`__ __`box.`__ __`img.`__|:sunflower: [MS-COCO, PASCAL VOC, Bees, CrowdHuman, Objects365](#semi-or-weak-supervised-object-detection)|\n|2021-09|Wuhan University of Science and Technology|Weakly Supervised Segmentation of COVID19 Infection with Scribble Annotation on CT Image|None|[Pattern Recognition](https://doi.org/10.1016/j.patcog.2021.108341)|__`scrib.`__ |:hospital: [COVID-19](#is-covid-dataset)|\n|2021-06|UC Berkeley|Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning|[github](https://github.com/twke18/SPML)|[ICLR](https://bair.berkeley.edu/blog/2021/07/22/spml/)|__`scrib.`__ __`point.`__ __`box.`__ __`img.`__|:sunflower: Pascal VOC 2012|\n|2021-03|Hong Kong University of Science and Technology|Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion|[github](https://hkchengrex.github.io/MiVOS/)|[CVPR](https://arxiv.org/pdf/2103.07941.pdf)|__`scrib.`__|:sunflower: [Interactive Video Object Segmentation](#TODO)|\n|2021-03|University of Edinburgh|Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates|[github](https://vios-s.github.io/multiscale-adversarial-attention-gates)|[TMI](https://ieeexplore.ieee.org/abstract/document/9389796)|__`scrib.`__|:hospital: [Heart Segmentation](#heart-segmentation), [Abdominal Segmentation](#abdominal-segmentation)|\n|2021-01|Element AI|A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images|[github](https://github.com/IssamLaradji/covid19_weak_supervision)|[WACV](https://ieeexplore.ieee.org/document/9423094/)|__`point.`__|:hospital: COVID-19|\n|2020-07|Australian National University|Weakly-Supervised Salient Object Detection via Scribble Annotations|[github](https://github.com/JingZhang617/Scribble_Saliency)|[CVPR](https://ieeexplore.ieee.org/document/9157788)|__`scrib.`__|:sunflower: [DUTS testing dataset, ECSSD, DUT, PASCAL-S, HKU-IS, THUR](#salient-object-detection)|\n|2020-09|Rutgers University|Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images|None|[TMI](https://ieeexplore.ieee.org/abstract/document/9116833)|__`point.`__ |:hospital: |\n|2020-06|Ulsan National Institute of Science and Technology|Scribble2Label: Scribble-Supervised Cell Segmentation via Self-Generating Pseudo-Labels with Consistency|[github](https://github.com/hvcl/scribble2label)|[MICCAI](https://link.springer.com/chapter/10.1007/978-3-030-59710-8_2)|__`scrib.`__|:hospital: [Cell segmentation](#cell-segmentation)|\n\n## Benchmark\n### Medical images \n#### Vestibular Schwannoma\n* [VS](https://www.nature.com/articles/s41597-021-01064-w)\n#### Brain Tumor Segmentation\n* [BraTS](https://doi.org/10.1109/tmi.2014.2377694)\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"images/pa-seg-result.png\" /\u003e\u003c/p\u003e \n\n#### [IS-COVID dataset](https://ieeexplore.ieee.org/stampPDF/getPDF.jsp?tp=\u0026arnumber=9098956\u0026ref=)\n\n|Label|Methods|dice|Jaccard|sensitivity|specificity|MAE|\n|---|---|---|---|---|---|---|\n|Scribble|p-UNet[55]|0.660|0.516|0.833|0.825|0.138|\n||WS0D[54]|0.684|0.533|0.842|0.871|0.114|\n||S2L[44]|0.708|0.550|0.805|0.926|0.091|\n||USTM-Net|0.725|0.582|0.854|0.967|0.086|\n|Full|U-Net[49]|0.736|0.595|0.867|0.961|0.082|\n\n#### [Lesion Segmentation (CC-COVID) dataset](https://www.cell.com/cell/pdf/S0092-8674(20)31071-0.pdf)\n\n\u003ctable\u003e\n\u003ctable style=\"text-align: center\"\u003e\n    \u003ctr\u003e\n        \u003ctd rowspan=\"2\"\u003eLabel\u003c/td\u003e\n        \u003ctd rowspan=\"2\"\u003eMethods\u003c/td\u003e\n        \u003ctd colspan=\"3\"\u003eConsolidation\u003c/td\u003e\n        \u003ctd colspan=\"3\"\u003eGround-Glass Opacity\u003c/td\u003e\n        \u003ctd colspan=\"3\"\u003eAverage\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eDice\u003c/td\u003e\n        \u003ctd\u003eSE\u003c/td\u003e\n        \u003ctd\u003eSP\u003c/td\u003e\n        \u003ctd\u003eDice\u003c/td\u003e\n        \u003ctd\u003eSE\u003c/td\u003e\n        \u003ctd\u003eSP\u003c/td\u003e\n        \u003ctd\u003eDice\u003c/td\u003e\n        \u003ctd\u003eSE\u003c/td\u003e\n        \u003ctd\u003eSP\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd rowspan=\"4\"\u003eScribble\u003c/td\u003e\n        \u003ctd\u003ep-UNet [55]\u003c/td\u003e\n        \u003ctd\u003e0.672 \u003c/td\u003e\n        \u003ctd\u003e0.806 \u003c/td\u003e\n        \u003ctd\u003e0.908 \u003c/td\u003e\n        \u003ctd\u003e0.643 \u003c/td\u003e\n        \u003ctd\u003e0.789 \u003c/td\u003e\n        \u003ctd\u003e0.894 \u003c/td\u003e\n        \u003ctd\u003e0.658 \u003c/td\u003e\n        \u003ctd\u003e0.798 \u003c/td\u003e\n        \u003ctd\u003e0.901 \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eWSOD [54]\u003c/td\u003e\n        \u003ctd\u003e0.695 \u003c/td\u003e\n        \u003ctd\u003e0.833 \u003c/td\u003e\n        \u003ctd\u003e0.917 \u003c/td\u003e\n        \u003ctd\u003e0.674 \u003c/td\u003e\n        \u003ctd\u003e0.801 \u003c/td\u003e\n        \u003ctd\u003e0.902 \u003c/td\u003e\n        \u003ctd\u003e0.685 \u003c/td\u003e\n        \u003ctd\u003e0.817 \u003c/td\u003e\n        \u003ctd\u003e0.910 \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eS2L [44]\u003c/td\u003e\n        \u003ctd\u003e0.724 \u003c/td\u003e\n        \u003ctd\u003e0.857 \u003c/td\u003e\n        \u003ctd\u003e0.934 \u003c/td\u003e\n        \u003ctd\u003e0.698 \u003c/td\u003e\n        \u003ctd\u003e0.840 \u003c/td\u003e\n        \u003ctd\u003e0.928 \u003c/td\u003e\n        \u003ctd\u003e0.711 \u003c/td\u003e\n        \u003ctd\u003e0.849 \u003c/td\u003e\n        \u003ctd\u003e0.931 \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eUSTM-Net\u003c/td\u003e\n        \u003ctd\u003e0.736 \u003c/td\u003e\n        \u003ctd\u003e0.862 \u003c/td\u003e\n        \u003ctd\u003e0.958 \u003c/td\u003e\n        \u003ctd\u003e0.709 \u003c/td\u003e\n        \u003ctd\u003e0.829 \u003c/td\u003e\n        \u003ctd\u003e0.947 \u003c/td\u003e\n        \u003ctd\u003e0.723 \u003c/td\u003e\n        \u003ctd\u003e0.846 \u003c/td\u003e\n        \u003ctd\u003e0.953 \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003ePoint\u003c/td\u003e\n        \u003ctd\u003eWSCL [18]\u003c/td\u003e\n        \u003ctd\u003e0.705 \u003c/td\u003e\n        \u003ctd\u003e0.827 \u003c/td\u003e\n        \u003ctd\u003e0.920 \u003c/td\u003e\n        \u003ctd\u003e0.681 \u003c/td\u003e\n        \u003ctd\u003e0.803 \u003c/td\u003e\n        \u003ctd\u003e0.916 \u003c/td\u003e\n        \u003ctd\u003e0.693 \u003c/td\u003e\n        \u003ctd\u003e0.815 \u003c/td\u003e\n        \u003ctd\u003e0.918 \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n        \u003ctd\u003eFull\u003c/td\u003e\n        \u003ctd\u003eU-Net [49]\u003c/td\u003e\n        \u003ctd\u003e0.748 \u003c/td\u003e\n        \u003ctd\u003e0.874 \u003c/td\u003e\n        \u003ctd\u003e0.966 \u003c/td\u003e\n        \u003ctd\u003e0.713 \u003c/td\u003e\n        \u003ctd\u003e0.825 \u003c/td\u003e\n        \u003ctd\u003e0.952 \u003c/td\u003e\n        \u003ctd\u003e0.731 \u003c/td\u003e\n        \u003ctd\u003e0.850 \u003c/td\u003e\n        \u003ctd\u003e0.959 \u003c/td\u003e\n    \u003c/tr\u003e\n\u003c/table\u003e\n\n#### Heart Segmentation\n* [ACDC dataset](https://www.creatis.insa-lyon.fr/Challenge/acdc/databases.html), [scribble available](https://vios-s.github.io/multiscale-adversarial-attention-gates/data)\n* [LVSC dataset](https://www.sciencedirect.com/science/article/abs/pii/S1361841513001217), [scribble generation](https://github.com/gvalvano/multiscale-adversarial-attention-gates/blob/fc05d70d411d20147075392c14fced274c1bf6ee/data_interface/scribble_generators/scribble_generators.py#L5)\n* [MSCMRseg dataset](https://zmiclab.github.io/zxh/0/mscmrseg19/index.html), [scribble available](https://github.com/BWGZK/CycleMix/tree/main/MSCMR_scribbles)\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"images/cyclemix.jpeg\" /\u003e\u003c/p\u003e \n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"images/luo_2022_miccai.jpg\" /\u003e\u003c/p\u003e \n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"images/scribble2D5.png\" /\u003e\u003c/p\u003e \n\n#### Abdominal Segmentation\n* [CHAOS dataset](https://chaos.grand-challenge.org/),[scribble generation](https://github.com/gvalvano/multiscale-adversarial-attention-gates/blob/fc05d70d411d20147075392c14fced274c1bf6ee/data_interface/scribble_generators/scribble_generators.py#L5)\n* result style in the table: (Dice) mean±std.\n\n|SupervisionType|Model|ACDC|LVSC|CHAOS-T1|CHAOS-T2|\n|----|---------|----|----|----|----|\n|Scribble|UNet pcE|79.0±0.06|62.3±0.09|34.4±0.06|37.5±0.06|\n|Scribble    | UNet wpcE       | 69.4±0.07 | 59.1±0.07 | 40.0±0.05 | 52.1±0.05 |\n| Scribble | UNet cRF| 69.6±0.07 | 60.4±0.08 | 40.5±0.05 | 44.7±0.06 |\n| Scribble | TS-UNet cRF     | 37.3±0.08 | 50.5±0.07 | 29.3±0.05 | 27.6±0.05 |\n| Scribble | PostDAE        | 69.0±0.06 | 58.6±0.07 | 29.1±0.06 | 35.5±0.05 |\n| Scribble         | UNet D          | 61.8±0.08 | 31.7±0.09 | 44.0±0.03 | 46.3±0.01 |\n| Scribble         | ACCL           | 82.6±0.05 | 65.9±0.08 | 48.3±0.07 | 49.7±0.05 |\n| Scribble         | [Valvano et al.](https://ieeexplore.ieee.org/abstract/document/9389796) | 84.3±0.04 | 65.5±0.08 | 56.8±0.05 | 57.8±0.04 |\n| Mask             | UNet UB         | 82.0±0.qs | 67.2±0.07 | 60.8±0.06 | 58.6±0.01 |\n| Mask             | UNet D UB       | 83.9±0.05 | 67.9±0.09 | 63.9±0.05 | 60.8±0.01 |\n\n#### Cell Segmentation\n* [EM](https://www.sci.utah.edu/~tolga/ResearchWebPages/em-segmentation.html)\u0026[Data Science Bowl 2018](https://www.kaggle.com/c/data-science-bowl-2018/)\u0026[MoNuSeg](https://ieeexplore.ieee.org/document/7872382)   \n* result style in the table: Dice[mIoU]\n\n|Label|Method|EM|DSB-BF|DSB-Fluo|DSB-Histo|MoNuSeg|\n|---|----|---|---|---|---|---|\n|Scribble|GrabCut[8]|0.5288[0.6066]|0.7328[0.7207]|0.8019[0.7815]|0.6969[0.5961]|0.1534[0.0703]|\n|Scribble|Pseudo-Label[6]|0.9126[0.9096]|0.6177[0.6826]|0.8109[0.8136]|0.7888[0.7096]|0.6113[0.5607]|\n|Scribble|pCEOnly[16]|0.9000[0.9032]|0.7954[0.7351]|0.8293[0.8375]|0.7804[0.7173]|0.6319[0.5766]|\n|Scribble|rLoss[16]|0.9108[0.9100]|0.7993[0.7280]|0.8334[0.8394]|0.7873[0.7177]|0.6337[0.5789]|\n|Scribble|[Scribble2Label](https://link.springer.com/chapter/10.1007/978-3-030-59710-8_2)|0.9208[0.9167]|0.8236[0.7663]|0.8426[0.8443]|0.7970[0.7246]|0.6408[0.5811]|\n|Point|Qu[13]|-|-|-|0.5544[0.7204]|0.6099[0.7127]|\n|Full|Full|0.9298[0.9149]|0.8774[0.7879]|0.8688[0.8390]|0.8134[0.7014]|0.7014[0.6677]|\n\n### Natural Images \n#### Camouflaged Object Detection\n* [COD10K](https://ieeexplore.ieee.org/document/9156837/)\n* [CAMO](https://www.sciencedirect.com/science/article/abs/pii/S1077314219300608)\n* [CHAMELEON](https://www.polsl.pl/rau6/chameleon-database-animal-camouflage-analysis/)\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"images/weak-cod.png\" /\u003e\u003c/p\u003e \n\n#### Semi or Weak-Supervised Object Detection\n* [MS-COCO](https://link.springer.com/chapter/10.1007/978-3-319-10602-1_48)\n* [PASCAL VOC](https://link.springer.com/article/10.1007/s11263-009-0275-4)\n\u003cp align=\"center\"\u003e\u003cimg width=\"50%\" src=\"images/omni-table3.png\" /\u003e\u003c/p\u003e \u003cp align=\"center\"\u003e\u003cimg width=\"50%\" src=\"images/omni-table4.png\" /\u003e\u003c/p\u003e \u003cp align=\"center\"\u003e\u003cimg width=\"50%\" src=\"images/omni-table5.png\" /\u003e\u003c/p\u003e \u003cp align=\"center\"\u003e\u003cimg width=\"50%\" src=\"images/omni-table6.png\" /\u003e\u003c/p\u003e \u003cp align=\"center\"\u003e\u003cimg width=\"50%\" src=\"images/omni-table7.png\" /\u003e\u003c/p\u003e \n\n* [Bees](https://lila.science/datasets/boxes-on-bees-and-pollen)\n* [CrowdHuman](https://arxiv.org/abs/1805.00123v1)\n* [Objects365](https://openaccess.thecvf.com/content_ICCV_2019/papers/Shao_Objects365_A_Large-Scale_High-Quality_Dataset_for_Object_Detection_ICCV_2019_paper.pdf)\n\n\n#### Salient Object Detection\n* [DUTS](https://ieeexplore.ieee.org/document/8099887)\n* [ECSSD](https://ieeexplore.ieee.org/document/6618997)\n* [DUT](https://ieeexplore.ieee.org/document/6619251)\n* [PASCAL-S](https://ieeexplore.ieee.org/document/6909437)\n* [HKU-IS](https://ieeexplore.ieee.org/document/7299184/)\n* [THUR](https://link.springer.com/article/10.1007/s00371-013-0867-4)\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"images/result-sod.png\" /\u003e\u003c/p\u003e \n\n### Others \n\n## Tutorial\n* 中文：\n1. https://zhuanlan.zhihu.com/p/81404885\n2. https://baijiahao.baidu.com/s?id=1632614040925107215\u0026wfr=spider\u0026for=pc\n* English：\n1. https://ai.stanford.edu/blog/weak-supervision\n2. https://www.snorkel.org/blog/weak-supervision\n3. Zhou Z H. [A brief introduction to weakly supervised learning](https://academic.oup.com/nsr/article/5/1/44/4093912). National science review, 2018, 5(1): 44-53.\n## Conclusion\n* This repository provides daily-update literature reviews, algorithms' implementation, and some examples of using PyTorch for weak-supervised image segmentation. The project is under development. \nIn the future, it will support 2D and 3D semi-supervised image segmentation and includes five widely-used algorithms' implementations.\n\t\t\n* In the next two or three months, we will provide more algorithms' implementations, examples, and pre-trained models.\n\n## Questions and Suggestions\n* If you have any questions or suggestions about this project, please contact me through email: `lichen14@nudt.edu.cn`. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flichen14%2Fawesome-weakly-supervised-segmentation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flichen14%2Fawesome-weakly-supervised-segmentation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flichen14%2Fawesome-weakly-supervised-segmentation/lists"}