{"id":610,"name":"Annotation Interface for Data-driven Ecology","description":"Tools for detecting wildlife in aerial images using active learning.","url":"https://github.com/microsoft/aerial_wildlife_detection","last_synced_at":"2026-04-28T08:30:20.334Z","repository":{"id":37736203,"uuid":"197671887","full_name":"microsoft/aerial_wildlife_detection","owner":"microsoft","description":"Tools for detecting wildlife in aerial images using active learning","archived":false,"fork":false,"pushed_at":"2026-03-30T15:57:10.000Z","size":35204,"stargazers_count":242,"open_issues_count":28,"forks_count":60,"subscribers_count":22,"default_branch":"master","last_synced_at":"2026-04-14T00:02:02.132Z","etag":null,"topics":["active-learning","aerial-imagery","aiforearth","conservation","wildlife"],"latest_commit_sha":null,"homepage":"","language":"Python","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/microsoft.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2019-07-18T23:58:41.000Z","updated_at":"2026-03-30T15:56:46.000Z","dependencies_parsed_at":"2023-09-21T19:09:06.991Z","dependency_job_id":"29fee61f-49d9-48a3-96ce-59558cc7a028","html_url":"https://github.com/microsoft/aerial_wildlife_detection","commit_stats":{"total_commits":744,"total_committers":14,"mean_commits":"53.142857142857146","dds":0.5362903225806452,"last_synced_commit":"06c36a5bc5d98c7618cade36711ade7a0f677c13"},"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/microsoft/aerial_wildlife_detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/microsoft","download_url":"https://codeload.github.com/microsoft/aerial_wildlife_detection/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32077837,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-21T02:38:07.213Z","status":"ssl_error","status_checked_at":"2026-04-21T02:38:06.559Z","response_time":128,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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"}},"owner":{"login":"microsoft","name":"Microsoft","uuid":"6154722","kind":"organization","description":"Open source projects and samples from Microsoft","email":"opensource@microsoft.com","website":"https://opensource.microsoft.com","location":"Redmond, WA","twitter":"OpenAtMicrosoft","company":null,"icon_url":"https://avatars.githubusercontent.com/u/6154722?v=4","repositories_count":7748,"last_synced_at":"2026-04-23T00:30:06.193Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/microsoft","funding_links":[],"total_stars":3890421,"followers":117846,"following":0,"created_at":"2022-11-02T16:20:12.368Z","updated_at":"2026-04-23T00:30:06.193Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/microsoft","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/microsoft/repositories"},"packages":[],"commits":{"id":1254290,"full_name":"microsoft/aerial_wildlife_detection","default_branch":"master","total_commits":748,"total_committers":16,"total_bot_commits":2,"total_bot_committers":2,"mean_commits":46.75,"dds":0.5387700534759359,"past_year_total_commits":2,"past_year_total_committers":2,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":1.0,"past_year_dds":0.5,"last_synced_at":"2026-04-27T03:34:52.036Z","last_synced_commit":"e9c47993ce293fb234264ac94da158e9fce0d0fc","created_at":"2023-03-27T11:31:53.551Z","updated_at":"2026-04-27T03:33:28.301Z","committers":[{"name":"bkellenb","email":"kudu@kuduvm.5svuschbwnqu5b5t3fbzyv3y5b.xx.internal.cloudapp.net","login":null,"count":345},{"name":"bkellenb","email":"pronghorn@pronghornvm.5svuschbwnqu5b5t3fbzyv3y5b.xx.internal.cloudapp.net","login":null,"count":159},{"name":"bkellenb","email":"benjamin.kellenberger@epfl.ch","login":"bkellenb","count":142},{"name":"=","email":"=","login":null,"count":47},{"name":"Dan Morris","email":"dmorris@cs.stanford.edu","login":"agentmorris","count":18},{"name":"szjarek","email":"szjarek@outlook.com","login":"szjarek","count":17},{"name":"amritagupta","email":"gupta.amrita20@gmail.com","login":"amritagupta","count":9},{"name":"Francesco Frassinelli","email":"francesco.frassinelli@nina.no","login":"frafra","count":2},{"name":"=","email":"benjamin.kellenberger@wur.nl","login":null,"count":2},{"name":"x4v13r64","email":"xavier.garceau-aranda@owasp.org","login":"x4v13r64","count":1},{"name":"microsoft-github-policy-service[bot]","email":"77245923+microsoft-github-policy-service[bot]","login":"microsoft-github-policy-service[bot]","count":1},{"name":"junxnone","email":"junchen0102@gmail.com","login":"junxnone","count":1},{"name":"dependabot[bot]","email":"49699333+dependabot[bot]","login":"dependabot[bot]","count":1},{"name":"Segu Riluvan","email":"riluvan@gmail.com","login":"navulirs","count":1},{"name":"Matthew Skiffington","email":"42245625+MattSkiff","login":"MattSkiff","count":1},{"name":"bkellenb","email":"root@kuduvm.5svuschbwnqu5b5t3fbzyv3y5b.xx.internal.cloudapp.net","login":null,"count":1}],"past_year_committers":[{"name":"x4v13r64","email":"xavier.garceau-aranda@owasp.org","login":"x4v13r64","count":1},{"name":"Segu Riluvan","email":"riluvan@gmail.com","login":"navulirs","count":1}],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-27T00:00:06.983Z","repositories_count":6219719,"commits_count":899556246,"contributors_count":34874003,"owners_count":1146042,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"microsoft/aerial_wildlife_detection","html_url":"https://github.com/microsoft/aerial_wildlife_detection","last_synced_at":"2026-04-23T07:24:01.502Z","status":"error","issues_count":47,"pull_requests_count":24,"avg_time_to_close_issue":2023875.7391304348,"avg_time_to_close_pull_request":13356029.368421054,"issues_closed_count":23,"pull_requests_closed_count":19,"pull_request_authors_count":14,"issue_authors_count":21,"avg_comments_per_issue":2.3404255319148937,"avg_comments_per_pull_request":0.6666666666666666,"merged_pull_requests_count":10,"bot_issues_count":0,"bot_pull_requests_count":5,"past_year_issues_count":0,"past_year_pull_requests_count":4,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":611570.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":2,"past_year_pull_request_authors_count":3,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":0.5,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":2,"past_year_merged_pull_requests_count":2,"created_at":"2023-05-09T10:35:40.285Z","updated_at":"2026-04-23T07:24:01.503Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/microsoft%2Faerial_wildlife_detection/issues","issue_labels_count":{},"pull_request_labels_count":{"dependencies":4,"python":2},"issue_author_associations_count":{"NONE":35,"CONTRIBUTOR":10,"COLLABORATOR":2},"pull_request_author_associations_count":{"CONTRIBUTOR":17,"NONE":6,"COLLABORATOR":1},"issue_authors":{"ctorney":9,"frafra":7,"AllenDun":3,"simbamangu":3,"mikeyEcology":3,"MattSkiff":3,"bkellenb":2,"scfulford":2,"YangZhangMizzou":2,"VLucet":2,"robmarkcole":1,"bw4sz":1,"marireeves":1,"HPL123":1,"frobin02":1,"JCAAUSFRA":1,"cstldrones":1,"stewartmacdonald":1,"valentinitnelav":1,"ryan-ntt":1,"jstabach":1},"pull_request_authors":{"frafra":5,"dependabot[bot]":4,"Infinite-Blue-1042":2,"MattSkiff":2,"szjarek":2,"kushalsingh-00":1,"bkellenb":1,"junxnone":1,"ctorney":1,"x4v13r64":1,"agentmorris":1,"microsoft-github-policy-service[bot]":1,"navulirs":1,"Forchapeatl":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-27T00:00:06.950Z","repositories_count":14426570,"issues_count":34458432,"pull_requests_count":112700256,"authors_count":11246548,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{"dependencies":2,"python":2},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{"CONTRIBUTOR":4},"past_year_issue_authors":{},"past_year_pull_request_authors":{"dependabot[bot]":2,"navulirs":1,"x4v13r64":1},"maintainers":[{"login":"bkellenb","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/bkellenb"}],"active_maintainers":[]},"events":{"total":{"MemberEvent":1,"PullRequestEvent":1,"ForkEvent":3,"WatchEvent":10,"IssueCommentEvent":2,"PushEvent":3,"CreateEvent":1},"last_year":{"MemberEvent":1,"PullRequestEvent":1,"ForkEvent":3,"WatchEvent":2,"IssueCommentEvent":2,"PushEvent":3,"CreateEvent":1}},"keywords":["active-learning","aerial-imagery","aiforearth","conservation","wildlife"],"dependencies":[{"ecosystem":"pypi","filepath":"docker/requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T21:30:47.370Z","updated_at":"2022-08-08T21:30:47.370Z","repository_link":"https://github.com/microsoft/aerial_wildlife_detection/blob/master/docker/requirements.txt","dependencies":[{"id":696376360,"package_name":"bottle","ecosystem":"pypi","requirements":"\u003e=0.12","direct":true,"kind":"runtime","optional":false},{"id":696376361,"package_name":"gunicorn","ecosystem":"pypi","requirements":"\u003e=19.9.0","direct":true,"kind":"runtime","optional":false},{"id":696376362,"package_name":"psycopg2","ecosystem":"pypi","requirements":"\u003e=2.8.2","direct":true,"kind":"runtime","optional":false},{"id":696376363,"package_name":"tqdm","ecosystem":"pypi","requirements":"\u003e=4.32.1","direct":true,"kind":"runtime","optional":false},{"id":696376364,"package_name":"bcrypt","ecosystem":"pypi","requirements":"\u003e=3.1.6","direct":true,"kind":"runtime","optional":false},{"id":696376365,"package_name":"netifaces","ecosystem":"pypi","requirements":"\u003e=0.10.9","direct":true,"kind":"runtime","optional":false},{"id":696376366,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696376367,"package_name":"Pillow","ecosystem":"pypi","requirements":"\u003e=2.2.1","direct":true,"kind":"runtime","optional":false},{"id":696376368,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696376369,"package_name":"requests","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696376370,"package_name":"celery","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696376371,"package_name":"opencv-python","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696376372,"package_name":"torch","ecosystem":"pypi","requirements":"==1.9.0","direct":true,"kind":"runtime","optional":false},{"id":696376373,"package_name":"torchvision","ecosystem":"pypi","requirements":"==0.10.0","direct":true,"kind":"runtime","optional":false},{"id":696376374,"package_name":"detectron2","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2022-08-08T21:30:48.050Z","updated_at":"2022-08-08T21:30:48.050Z","repository_link":"https://github.com/microsoft/aerial_wildlife_detection/blob/master/requirements.txt","dependencies":[{"id":696386057,"package_name":"bottle","ecosystem":"pypi","requirements":"\u003e=0.12","direct":true,"kind":"runtime","optional":false},{"id":696386213,"package_name":"gunicorn","ecosystem":"pypi","requirements":"\u003e=19.9.0","direct":true,"kind":"runtime","optional":false},{"id":696386227,"package_name":"psycopg2-binary","ecosystem":"pypi","requirements":"\u003e=2.8.2","direct":true,"kind":"runtime","optional":false},{"id":696386229,"package_name":"tqdm","ecosystem":"pypi","requirements":"\u003e=4.32.1","direct":true,"kind":"runtime","optional":false},{"id":696386231,"package_name":"bcrypt","ecosystem":"pypi","requirements":"\u003e=3.1.6","direct":true,"kind":"runtime","optional":false},{"id":696386233,"package_name":"netifaces","ecosystem":"pypi","requirements":"\u003e=0.10.9","direct":true,"kind":"runtime","optional":false},{"id":696386235,"package_name":"python-dateutil","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696386237,"package_name":"Pillow","ecosystem":"pypi","requirements":"\u003e=2.2.1","direct":true,"kind":"runtime","optional":false},{"id":696386239,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696386240,"package_name":"requests","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696386242,"package_name":"celery","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696386244,"package_name":"opencv-python","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":696386246,"package_name":"torch","ecosystem":"pypi","requirements":"==1.9.0","direct":true,"kind":"runtime","optional":false},{"id":696386248,"package_name":"torchvision","ecosystem":"pypi","requirements":"==0.10.0","direct":true,"kind":"runtime","optional":false},{"id":696386250,"package_name":"detectron2","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"docker","filepath":"docker/Dockerfile","sha":null,"kind":"manifest","created_at":"2023-02-08T13:31:00.712Z","updated_at":"2023-02-08T13:31:00.712Z","repository_link":"https://github.com/microsoft/aerial_wildlife_detection/blob/master/docker/Dockerfile","dependencies":[{"id":7453757338,"package_name":"pytorch/pytorch","ecosystem":"docker","requirements":"1.9.0-cuda11.1-cudnn8-devel","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"docker/docker-compose.yml","sha":null,"kind":"manifest","created_at":"2023-02-08T13:31:00.767Z","updated_at":"2023-02-08T13:31:00.767Z","repository_link":"https://github.com/microsoft/aerial_wildlife_detection/blob/master/docker/docker-compose.yml","dependencies":[{"id":7453757355,"package_name":"aide_app","ecosystem":"docker","requirements":"latest","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2023-09-21T19:09:06.735Z","updated_at":"2023-09-21T19:09:06.735Z","repository_link":"https://github.com/microsoft/aerial_wildlife_detection/blob/master/setup.py","dependencies":[]}],"score":8.371010681238156,"created_at":"2023-09-11T11:54:35.346Z","updated_at":"2026-04-28T08:30:20.335Z","avatar_url":"https://github.com/microsoft.png","language":"Python","category":"Biosphere","sub_category":"Terrestrial Wildlife","monthly_downloads":0,"total_dependent_repos":0,"total_dependent_packages":0,"readme":"# AIDE: Annotation Interface for Data-driven Ecology\n\nAIDE is two things in one: \u003ci\u003ea tool for manually annotating images\u003c/i\u003e and \u003ci\u003ea tool for training and running machine (deep) learning models\u003c/i\u003e. Those two things are coupled in an \u003ci\u003eactive learning loop\u003c/i\u003e: the human annotates a few images, the system trains a model, that model is used to make predictions and to select more images for the human to annotate, etc.\n   \nMore generally, AIDE is a modular Web framework for labeling image datasets with AI assistance.  AIDE is configurable for a variety of tasks, but it is particularly intended for ecological applications, such as the acceleration wildlife surveys that use aerial images. \n\nAIDE is primarily developed by [Benjamin Kellenberger](https://bkellenb.github.io), supported by the [Microsoft AI for Earth](https://www.microsoft.com/en-us/ai/ai-for-earth) program.\n\n\n\n## Contents\n* [Highlights](#highlights)\n* [News](#news)\n* [Demo](#demo)\n* [Installation and launching AIDE](#installation-and-launching-aide)\n* [AI models in AIDE](#ai-models-in-aide)\n  * [Built-in AI models](#built-in-ai-models)\n  * [Writing your own AI model](#writing-your-own-ai-model)\n* [Publications and References](#publications-and-references)\n* [Contributing](#contributing)\n\n\n\n## Highlights\n\n* **Powerful:** AIDE explicitly integrates humans and AI models in an annotation loop.\n* **Fast:** AIDE has been designed with speed in mind, both in terms of computations and workflow.\n* **Flexible:** The framework allows full customizability, from hyperparameters to models to annotation types to libraries. It provides:\n    * Support for image classification, point annotations, and bounding boxes (object detection)\n    * Many deep learning-based AI models and Active Learning criteria built-in\n    * Interfaces for custom AI models and criteria, using any framework or library you want (see how to [write your own model](doc/custom_model.md)).\n* **Fully featured:** Beyond image labeling and model training, AIDE has management and graphical user/machine performance evaluation tools built-in, right in the web browser, allowing for advanced, manual label quality checks.\n* **Modular:** AIDE is separated into individual _modules_, each of which can be run on separate machines for scalability. It even supports on-the-fly addition of computational workers for computationally intensive model training!\n\n![AIDE highlights](doc/figures/AIDE_workflow.png)\n\n\n\n## News\n\n### AIDE v2.1 is out\n\nAIDE v2.1 is out! This includes a new interactive installer for Debian/Ubuntu systems as well as a plethora of bug fixes.\n\n\n[Older news](doc/news.md)\n\n\n\n\n## Demo\n\nA demo of AIDE v2 can be accessed **[here](http://aidedemo.westeurope.cloudapp.azure.com:8080/)**.\n\nThis demo allows exploring the annotation front-end with a number of example datasets, including:\n* **[Image labels](http://aidedemo.westeurope.cloudapp.azure.com:8080/snapshot_serengeti/interface)** on the [Snapshot Serengeti camera traps dataset](http://lila.science/datasets/snapshot-serengeti)\n* **[Points](http://aidedemo.westeurope.cloudapp.azure.com:8080/vgg_penguins/interface)** on the [VGG Penguins dataset](http://www.robots.ox.ac.uk/~vgg/data/penguins/)\n* **[Bounding boxes](http://aidedemo.westeurope.cloudapp.azure.com:8080/arcticseals/interface)** on the [NOAA Arctic Seals aerial imagery](http://lila.science/datasets/arcticseals)\n* **[Semantic segmentation](http://aidedemo.westeurope.cloudapp.azure.com:8080/landcover/interface)** on the [Chesapeake Land Cover satellite imagery](http://lila.science/datasets/chesapeakelandcover)\n\n\n\n\n## Installation and launching AIDE\n\nSee [here](doc/install_overview.md).\n\n\n\n\n## AI models in AIDE\n\n### Built-in AI models\n\n\nAIDE ships with a set of built-in models that can be configured and customized:\n\n| Label type | AI model | Model variants / backbones | More info |\n|-|-|-|-|\n| Image labels | AlexNet | AlexNet | [paper](https://arxiv.org/abs/1404.5997) |\n|  | DenseNet | DenseNet-161 | [paper](https://arxiv.org/abs/1608.06993) |\n|  | MNASNet | MNASNet | [paper](https://arxiv.org/abs/1807.11626) |\n|  | MobileNet | MobileNet V2 | [paper](https://arxiv.org/abs/1801.04381) |\n|  | ResNet | ResNet-18; ResNet-34; ResNet-50; ResNet-101; ResNet-152 | [paper](https://arxiv.org/abs/1512.03385) |\n|  | ResNeXt | ResNeXt-50; ResNeXt-101 | [paper](https://arxiv.org/abs/1611.05431) |\n|  | ShuffleNet | ShuffleNet V2 | [paper](https://arxiv.org/abs/1807.11164) |\n|  | SqueezeNet | SqueezeNet | [paper](https://arxiv.org/abs/1602.07360) |\n|  | VGG | VGG-16 | [paper](https://arxiv.org/abs/1409.1556) |\n|  | Wide ResNet | Wide ResNet-50; Wide ResNet-101 | [info](https://pytorch.org/vision/stable/models.html#wide-resnet) |\n| Bounding boxes | Faster R-CNN | with ResNet-50 (PASCAL VOC); with ResNet-50 (MS-COCO); with ResNeXt-101 FPN (MS-COCO) | [paper](https://arxiv.org/pdf/1506.01497.pdf), [implementation details](https://github.com/facebookresearch/detectron2/blob/master/MODEL_ZOO.md#faster-r-cnn) |\n|  | RetinaNet | with ResNet-50 FPN (MS-COCO); with ResNet-101 FPN (MS-COCO) | [paper](https://openaccess.thecvf.com/content_ICCV_2017/papers/Lin_Focal_Loss_for_ICCV_2017_paper.pdf), [implementation details](https://github.com/facebookresearch/detectron2/blob/master/MODEL_ZOO.md#retinanet) |\n|  | TridentNet | with ResNet-50; ResNet-101 (MS-COCO) | [paper](https://arxiv.org/abs/1901.01892), [implementation details](https://github.com/facebookresearch/detectron2/tree/master/projects/TridentNet)\n| Segmentation masks | DeepLabV3+ | with modified ResNet-101 (Cityscapes) | [paper](http://openaccess.thecvf.com/content_ECCV_2018/papers/Liang-Chieh_Chen_Encoder-Decoder_with_Atrous_ECCV_2018_paper.pdf), [implementation details](https://github.com/facebookresearch/detectron2/tree/master/projects/DeepLab) |\n\n\nAll models can be configured in various ways through the AI model settings page in the Web browser. They all are pre-trained on [ImageNet](https://ieeexplore.ieee.org/document/5206848) unless specified otherwise.\nTo use one of the built-in models, simply import the requested one to your project through the Model Marketplace in the Web browser and start training/predicting!\n\n\n\n\n### Writing your own AI model\nAIDE is fully modular and supports custom AI models, as long as they provide a Python interface and can handle at least one of the different annotation and prediction types appropriately.\nWe greatly welcome contributions and are happy to help in the implementation of your custom models!\n\nSee [here](doc/custom_model.md) for instructions on implementing custom models into AIDE.\n\n\n\n## Publications and References\n\nPlease cite the following paper if you use AIDE in your work:\n\nKellenberger, Benjamin, Devis Tuia, and Dan Morris. \"AIDE: Accelerating image‐based ecological surveys with interactive machine learning.\" Methods in Ecology and Evolution 11(12), 1716-1727.\nDOI: [10.1111/2041-210X.13489](https://doi.org/10.1111/2041-210X.13489).\n\n```BibTeX\n@article{kellenberger2020aide,\n  title={AIDE: Accelerating image-based ecological surveys with interactive machine learning},\n  author={Kellenberger, Benjamin and Tuia, Devis and Morris, Dan},\n  journal={Methods in Ecology and Evolution},\n  volume={11},\n  number={12},\n  pages={1716--1727},\n  year={2020},\n  publisher={Wiley Online Library}\n}\n```\n\n\n\nIf you use AIDE, we would be happy to hear from you! Please send us an [E-mail](mailto:benjamin.kellenberger@epfl.ch) with a little bit of info about your use case; besides getting to know the fellow usership of our software, this also enables us to provide somewhat more tailored support for you if needed. \nThank you very much.\n\n\n## Contributing\n\nThis project welcomes contributions and suggestions.  Most contributions require you to agree to a\nContributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us\nthe rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.\n\nWhen you submit a pull request, a CLA bot will automatically determine whether you need to provide\na CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions\nprovided by the bot. You will only need to do this once across all repos using our CLA.\n\nThis project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).\nFor more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or\ncontact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.\n","funding_links":[],"readme_doi_urls":["https://doi.org/10.1111/2041-210X.13489"],"works":{"https://doi.org/10.1111/2041-210X.13489":{"id":"https://openalex.org/W3088087146","doi":"https://doi.org/10.1111/2041-210x.13489","title":"AIDE: Accelerating image‐based ecological surveys with interactive machine learning","display_name":"AIDE: Accelerating image‐based ecological surveys with interactive machine learning","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3088087146","doi":"https://doi.org/10.1111/2041-210x.13489","mag":"3088087146"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1111/2041-210x.13489","pdf_url":"https://besjournals.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/2041-210X.13489","source":{"id":"https://openalex.org/S1131227","display_name":"Methods in Ecology and Evolution","issn_l":"2041-210X","issn":["2041-210X"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310320503","host_organization_name":"Wiley-Blackwell","host_organization_lineage":["https://openalex.org/P4310320503","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley-Blackwell","Wiley"],"type":"journal"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://besjournals.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/2041-210X.13489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055174808","display_name":"Benjamin Kellenberger","orcid":"https://orcid.org/0000-0002-2902-2014"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University \u0026 Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Benjamin Kellenberger","raw_affiliation_string":"Laboratory of Geo‐Information Science and Remote Sensing Wageningen University \u0026amp; Research Wageningen The Netherlands; Microsoft AI for Earth, Seattle, WA, USA","raw_affiliation_strings":["Laboratory of Geo‐Information Science and Remote Sensing Wageningen University \u0026amp; Research Wageningen The Netherlands","Microsoft AI for Earth, Seattle, WA, USA"]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005192117","display_name":"Devis Tuia","orcid":"https://orcid.org/0000-0003-0374-2459"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University \u0026 Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]},{"id":"https://openalex.org/I5124864","display_name":"École Polytechnique Fédérale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH","NL"],"is_corresponding":false,"raw_author_name":"Devis Tuia","raw_affiliation_string":"Environmental Computational Science and Earth Observation Laboratory Ecole Polytechnique Fédérale de Lausanne (EPFL) Sion Switzerland; Laboratory of Geo‐Information Science and Remote Sensing Wageningen University \u0026amp; Research Wageningen The Netherlands","raw_affiliation_strings":["Environmental Computational Science and Earth Observation Laboratory Ecole Polytechnique Fédérale de Lausanne (EPFL) Sion Switzerland","Laboratory of Geo‐Information Science and Remote Sensing Wageningen University \u0026amp; Research Wageningen The Netherlands"]},{"author_position":"last","author":{"id":"https://openalex.org/A5010437765","display_name":"Dan Morris","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Morris","raw_affiliation_string":"Microsoft AI for Earth, Seattle, WA, USA","raw_affiliation_strings":["Microsoft AI for Earth, Seattle, WA, USA"]}],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055174808"],"corresponding_institution_ids":["https://openalex.org/I913481162","https://openalex.org/I1290206253"],"apc_list":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"apc_paid":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":18,"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"11","issue":"12","first_page":"1716","last_page":"1727"},"is_retracted":false,"is_paratext":false,"keywords":[{"keyword":"ecological surveys","score":0.639},{"keyword":"interactive machine learning","score":0.5011},{"keyword":"aide","score":0.3282},{"keyword":"machine learning","score":0.3135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916459},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.70151204},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6048469},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5121627},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.45284122},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.43003702},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4126989},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38197282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3299281},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32474613},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3225639},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.13245884},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1111/2041-210x.13489","pdf_url":"https://besjournals.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/2041-210X.13489","source":{"id":"https://openalex.org/S1131227","display_name":"Methods in Ecology and Evolution","issn_l":"2041-210X","issn":["2041-210X"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310320503","host_organization_name":"Wiley-Blackwell","host_organization_lineage":["https://openalex.org/P4310320503","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley-Blackwell","Wiley"],"type":"journal"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/282103","pdf_url":"https://infoscience.epfl.ch/record/282103/files/2041-210X.13489.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique Fédérale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1111/2041-210x.13489","pdf_url":"https://besjournals.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/2041-210X.13489","source":{"id":"https://openalex.org/S1131227","display_name":"Methods in Ecology and Evolution","issn_l":"2041-210X","issn":["2041-210X"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310320503","host_organization_name":"Wiley-Blackwell","host_organization_lineage":["https://openalex.org/P4310320503","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley-Blackwell","Wiley"],"type":"journal"},"license":"cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.42},{"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production","score":0.19},{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.18}],"grants":[{"funder":"https://openalex.org/F4320309480","funder_display_name":"Nvidia","award_id":null}],"referenced_works_count":40,"referenced_works":["https://openalex.org/W1506491340","https://openalex.org/W1901129140","https://openalex.org/W2078643436","https://openalex.org/W2080655919","https://openalex.org/W2089781772","https://openalex.org/W2108598243","https://openalex.org/W2110764733","https://openalex.org/W2143897835","https://openalex.org/W2194775991","https://openalex.org/W2319805499","https://openalex.org/W2331725058","https://openalex.org/W2413367505","https://openalex.org/W2433056695","https://openalex.org/W2565639579","https://openalex.org/W2727886734","https://openalex.org/W2752508182","https://openalex.org/W2763907668","https://openalex.org/W2769210209","https://openalex.org/W2774881190","https://openalex.org/W2783453650","https://openalex.org/W2802498826","https://openalex.org/W2804935296","https://openalex.org/W2810030371","https://openalex.org/W2895082331","https://openalex.org/W2901771398","https://openalex.org/W2919115771","https://openalex.org/W2921149812","https://openalex.org/W2921243212","https://openalex.org/W2921499963","https://openalex.org/W2932685513","https://openalex.org/W2945020140","https://openalex.org/W2950895784","https://openalex.org/W2952113774","https://openalex.org/W2956586819","https://openalex.org/W2963351448","https://openalex.org/W2963556638","https://openalex.org/W2981630388","https://openalex.org/W2992135859","https://openalex.org/W3007017931","https://openalex.org/W4288076010"],"related_works":["https://openalex.org/W2134017072","https://openalex.org/W2915208987","https://openalex.org/W1940452713","https://openalex.org/W2152256925","https://openalex.org/W2005567565","https://openalex.org/W2806040249","https://openalex.org/W2098714418","https://openalex.org/W848768768","https://openalex.org/W1538652242","https://openalex.org/W1490523903"],"ngrams_url":"https://api.openalex.org/works/W3088087146/ngrams","abstract_inverted_index":{"Abstract":[0],"Ecological":[1],"surveys":[2,26],"increasingly":[3],"rely":[4],"on":[5],"large‐scale":[6],"image":[7,57,171],"datasets,":[8],"typically":[9],"terabytes":[10],"of":[11,23,27,33,36,56,140,168],"imagery":[12],"for":[13,43,59,153,164,180],"a":[14,94,131,138,165],"single":[15],"survey.":[16],"The":[17],"ability":[18],"to":[19,52,78,102,114,123,130,159],"collect":[20],"this":[21],"volume":[22],"data":[24],"allows":[25],"unprecedented":[28],"scale,":[29],"at":[30,182],"the":[31,54,79,104,107,124,157],"cost":[32],"expansive":[34],"volumes":[35],"photo‐interpretation":[37],"labour.":[38],"We":[39],"present":[40],"Annotation":[41,151],"Interface":[42,152],"Data‐driven":[44,154],"Ecology":[45,155],"(AIDE),":[46],"an":[47,64],"open‐source":[48,175],"web":[49],"framework":[50],"designed":[51],"alleviate":[53],"task":[55],"annotation":[58,162],"ecological":[60],"surveys.":[61],"AIDE":[62,85,136,173],"employs":[63],"easy‐to‐use":[65],"and":[66,76,89,106,176],"customisable":[67,132],"labelling":[68],"interface":[69],"that":[70],"supports":[71],"multiple":[72,82],"users,":[73],"database":[74],"storage":[75],"scalability":[77],"cloud":[80],"and/or":[81],"machines.":[83],"Moreover,":[84],"closely":[86],"integrates":[87],"users":[88,125],"machine":[90],"learning":[91,134,142],"models":[92,143],"into":[93],"feedback":[95],"loop,":[96],"where":[97],"user‐provided":[98],"annotations":[99],"are":[100,120],"employed":[101],"re‐train":[103],"model,":[105],"latter":[108],"is":[109,174],"applied":[110],"over":[111],"unlabelled":[112],"images":[113],"e.g.":[115],"identify":[116],"wildlife.":[117],"These":[118],"predictions":[119],"then":[121],"presented":[122],"in":[126],"optimised":[127],"order,":[128],"according":[129],"active":[133],"criterion.":[135],"has":[137,156],"number":[139],"deep":[141],"built‐in,":[144],"but":[145],"also":[146],"accepts":[147],"custom":[148],"model":[149],"implementations.":[150],"potential":[158],"greatly":[160],"accelerate":[161],"tasks":[163],"wide":[166],"range":[167],"researches":[169],"employing":[170],"data.":[172],"can":[177],"be":[178],"downloaded":[179],"free":[181],"https://github.com/microsoft/aerial_wildlife_detection":[183],".":[184]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3088087146","counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2023-12-12T04:10:55.767980","created_date":"2020-10-01"}},"citation_counts":{"https://doi.org/10.1111/2041-210X.13489":18},"total_citations":18,"keywords_from_contributors":["cameratraps","ecology","megadetector"],"project_url":"https://ost.ecosyste.ms/api/v1/projects/610","html_url":"https://ost.ecosyste.ms/projects/610"}