{"id":24523581,"url":"https://github.com/yc-cui/super-ad","last_synced_at":"2026-04-27T01:31:47.356Z","repository":{"id":272275012,"uuid":"916046646","full_name":"yc-cui/Super-AD","owner":"yc-cui","description":"Rethinking Identity Mapping in Self-Supervised Hyperspectral Anomaly Detection: A Unified Perspective on Network Optimization","archived":false,"fork":false,"pushed_at":"2025-02-16T23:21:00.000Z","size":5482,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-15T14:12:35.049Z","etag":null,"topics":["deep-learning","hyperspectral-anomaly-detection","hyperspectral-image-classification","image-processing","neural-network","pytorch","segmentation","self-supervised","unified-framework"],"latest_commit_sha":null,"homepage":"","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/yc-cui.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":"2025-01-13T11:00:11.000Z","updated_at":"2025-02-21T14:24:04.000Z","dependencies_parsed_at":"2025-01-13T12:22:11.831Z","dependency_job_id":"8879b98b-aff5-4a20-886d-750b3667ba27","html_url":"https://github.com/yc-cui/Super-AD","commit_stats":null,"previous_names":["yc-cui/super-ad"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yc-cui%2FSuper-AD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yc-cui%2FSuper-AD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yc-cui%2FSuper-AD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yc-cui%2FSuper-AD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yc-cui","download_url":"https://codeload.github.com/yc-cui/Super-AD/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243738980,"owners_count":20340002,"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","hyperspectral-anomaly-detection","hyperspectral-image-classification","image-processing","neural-network","pytorch","segmentation","self-supervised","unified-framework"],"created_at":"2025-01-22T04:15:55.560Z","updated_at":"2026-04-27T01:31:47.350Z","avatar_url":"https://github.com/yc-cui.png","language":null,"readme":"# Accepted to TGRS2025: Overcoming the Identity Mapping Problem in Self-Supervised Hyperspectral Anomaly Detection\n\n\nThis repository contains a training script for the SuperAD model, designed for self-supervised anomaly detection overcoming the identity mapping problem. The script utilizes PyTorch Lightning for efficient training and logging, and it supports integration with Weights \u0026 Biases (Wandb) for experiment tracking.\n\n\n\n## Network Architecture\n\n![](assets/overview.png)\n\n\n\n## Requirements\n\n```bash\nconda env create -f environment.yml\nconda activate HAD\n```\n\n## Training\n\n```bash\npython train.py --data_name \u003cdata_name\u003e\n```\n\nThe `data_name` can be modified in the `name2dir.py` file, you can also add your own data by modifying the `name2dir.py` file.\n\nYou can refer to `slic_viz.ipynb` for generating the SLIC superpixel for your own data.\n\nThe log file will be saved in the `logs` folder, we provide an example log file in the `logs/HAD.SuperADTrainer/log_d=1__l=OBPM_k=3_w=5_b=1_a=1` folder.\n\nTo achieve better results, parameters such as the number of segments and the window size need to be tuned.\n\n### Arguments\n\nThe script accepts the following command-line arguments, parameters may be tuned for different datasets to achieve better performance:\n\n- --data_name: Name of the dataset to be used (default: “1_”).\n- --epochs: Number of training epochs (default: 1000).\n- --lr: Learning rate for the optimizer (default: 1e-3).\n- --a: Alpha parameter for the model (default: 1).\n- --b: Beta parameter for the model (default: 1).\n- --kernel_size: Size of the convolutional kernel (default: 3).\n- --window_size: Size of the sliding window (default: 5).\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyc-cui%2Fsuper-ad","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyc-cui%2Fsuper-ad","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyc-cui%2Fsuper-ad/lists"}