{"id":22068311,"url":"https://github.com/abc-125/segad","last_synced_at":"2025-07-24T06:30:45.830Z","repository":{"id":230627138,"uuid":"766445395","full_name":"abc-125/segad","owner":"abc-125","description":"Segmentation-based Anomaly Detector (SegAD)","archived":false,"fork":false,"pushed_at":"2024-05-14T15:19:18.000Z","size":25,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-05-15T01:21:49.042Z","etag":null,"topics":["anomaly-detection","anomalydetection"],"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/abc-125.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":"2024-03-03T09:38:11.000Z","updated_at":"2024-05-14T15:19:22.000Z","dependencies_parsed_at":"2024-05-12T15:26:16.331Z","dependency_job_id":"d4d59410-4837-480a-acae-7b746b66472d","html_url":"https://github.com/abc-125/segad","commit_stats":null,"previous_names":["abc-125/segad"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abc-125%2Fsegad","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abc-125%2Fsegad/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abc-125%2Fsegad/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abc-125%2Fsegad/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/abc-125","download_url":"https://codeload.github.com/abc-125/segad/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227421280,"owners_count":17775006,"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":["anomaly-detection","anomalydetection"],"created_at":"2024-11-30T20:03:55.217Z","updated_at":"2025-07-24T06:30:45.275Z","avatar_url":"https://github.com/abc-125.png","language":"Python","funding_links":[],"categories":["Paper List"],"sub_categories":["Follow-up Papers"],"readme":"# Supervised Anomaly Detection for Complex Industrial Images\nOfficial code for our CVPR 2024 [paper](https://arxiv.org/abs/2405.04953)\n\n[VAD repository](https://github.com/abc-125/vad)\n\n## Get Started \n\n### Environment\n```bash\npip install -r requirements.txt\n```\n\n### Data\n1. Download [segmentation maps for VisA](https://drive.google.com/file/d/1ZVMxtb6PY958qigxAQcLEifWsRdnLaI4/view?usp=sharing).\n2. Download [anomaly maps for EfficientAD](https://drive.google.com/file/d/1mknzBIE6Heqfr5_BQIFOojzuPDQG2o_O/view?usp=sharing).\n3. Download [anomaly maps for RD4AD](https://drive.google.com/file/d/1Pap5-8x74_AROFRxjcBvIu9XdqvzHMs8/view?usp=sharing).\n4. The data structure should look as follows:\n```shell\ndata\n|-- visa_segm\n|-- anomaly_maps\n|-----|--efficient_ad\n|-----|--rd4ad\n```\n\n### Train and evaluate\nOnly VisA dataset is available for now. List of available models: `[\"efficient_ad\", \"rd4ad\", \"all_ad\"]`. `\"all_ad\"` includes both EfficientAD and RD4AD.\n```bash\npython main.py --model efficient_ad\n```\n\n## Results\nCl. AUROC (image-level) for SegAD with different sources of anomaly maps.\n\n|   model            |  mean  | candle | capsules  | cashew | chewinggum  | fryum  | macaroni1 | macaroni2 | pcb1 | pcb2 | pcb3 | pcb4 | pipe_fryum |\n| -------------------| :----: | :----: | :-------: | :----: | :---------: | :----: | :-------: | :-------: | :---:| :---:| :---:| :---:| :--------: |\n| RD4AD + SegAD      | 95.3   | 98.5   | 80.2      | 98.9   | 99.4        | 96.1   | 97.4      | 90.7      | 96.4 | 96.3 | 94.1 | 99.9 | 95.8       |\n| EfficientAD + SegAD| 98.3   | 98.7   | 89.7      | 98.6   | 99.9        | 98.6   | 99.5      | 98.1      | 99.5 | 99.7 | 98.4 | 99.3 | 99.2       |\n| All AD + SegAD     | 98.4   | 99.0   | 90.7      | 99.0   | 99.9        | 98.5   | 99.4      | 98.1      | 99.2 | 99.7 | 98.3 | 99.8 | 99.1       |\n\n## Acknowledgement\n\nWe use [EfficientAD](https://github.com/nelson1425/EfficientAD) and [Anomalib](https://github.com/openvinotoolkit/anomalib/tree/main) for baseline anomaly detection models. We are thankful for their amazing work!\n\n## Citation\nPlease cite this paper if it helps your project:\n```\n@inproceedings{baitieva2024supervised,\n      title={Supervised Anomaly Detection for Complex Industrial Images}, \n      author={Aimira Baitieva and David Hurych and Victor Besnier and Olivier Bernard},\n      booktitle={CVPR},\n      year={2024} \n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabc-125%2Fsegad","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabc-125%2Fsegad","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabc-125%2Fsegad/lists"}