{"id":18631127,"url":"https://github.com/aimagelab/novelty-detection","last_synced_at":"2025-04-13T04:10:28.953Z","repository":{"id":47124542,"uuid":"157761713","full_name":"aimagelab/novelty-detection","owner":"aimagelab","description":"Latent space autoregression for novelty detection.","archived":false,"fork":false,"pushed_at":"2022-12-12T11:13:01.000Z","size":491,"stargazers_count":196,"open_issues_count":10,"forks_count":60,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-03-24T09:21:17.871Z","etag":null,"topics":["anomaly-detection","computer-vision","cvpr2019","deep-learning","novelty-detection","unsupervised-learning"],"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/aimagelab.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}},"created_at":"2018-11-15T19:28:38.000Z","updated_at":"2024-08-12T19:43:21.000Z","dependencies_parsed_at":"2023-01-27T18:15:38.786Z","dependency_job_id":null,"html_url":"https://github.com/aimagelab/novelty-detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aimagelab%2Fnovelty-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aimagelab%2Fnovelty-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aimagelab%2Fnovelty-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aimagelab%2Fnovelty-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aimagelab","download_url":"https://codeload.github.com/aimagelab/novelty-detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248661704,"owners_count":21141450,"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","computer-vision","cvpr2019","deep-learning","novelty-detection","unsupervised-learning"],"created_at":"2024-11-07T05:05:40.817Z","updated_at":"2025-04-13T04:10:28.848Z","avatar_url":"https://github.com/aimagelab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Latent Space Autoregression for Novelty Detection\n\nThis repository contains Pytorch code to replicate experiments in the CVPR19 paper \"Latent Space Autoregression for Novelty Detection\".\n\nPlease cite with the following BibTeX:\n```\n@inproceedings{abati2019latent,\n  title={{Latent Space Autoregression for Novelty Detection}},\n  author={Abati, Davide and Porrello, Angelo and Calderara, Simone and Cucchiara, Rita},\n  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition},\n  year={2019}\n}\n```\n\n![sample results](images/model.png)\n\nSpecifically, performs:\n* one class classification on MNIST.\n* one class classification on CIFAR-10.\n* video anomaly detection on UCSD Ped2.\n* video anomaly detection on ShanghaiTech.\n\n### 0 - Clone this repo\nFirst things first, clone this repository locally via git.\n```\ngit clone https://github.com/cvpr19-858/novelty-detection.git\ncd novelty-detection\n```\n\n### 1 - Environment\nThis code runs on Python 3.6.\nThe easiest way to set up the environment is via `pip` and the file `requirements.txt`:\n```\npip install -r requirements.txt\n```\n\n### 2 - Datasets\nMNIST and CIFAR-10 will be downloaded for you by torchvision. \n\nYou still need to download [UCSD Ped](http://www.svcl.ucsd.edu/projects/anomaly/UCSD_Anomaly_Dataset.tar.gz) and \n[ShanghaiTech](https://onedrive.live.com/?authkey=%21AMqh2fTSemfrokE\u0026cid=3705E349C336415F\u0026id=3705E349C336415F%2172436\u0026parId=3705E349C336415F%215109\u0026o=OneUp). After download, please unpack them into the `data` folder as follows\n\n```\ntar -xzvf \u003cpath-to-UCSD_Anomaly_Dataset.tar.gz\u003e -C data\ntar -xzvf \u003cpath-to-shanghaitech.tar.gz\u003e -C data\n```\n\n### 3 - Model checkpoints\nCheckpoints for all trained models are available [here](https://ailb-web.ing.unimore.it/publicfiles/drive/lsa-novelty-detection/checkpoints.tar.gz).\n\nPlease untar them into the `checkpoints` folder as follows:\n```\ntar -xzvf \u003cpath-to-tar.gz\u003e -C checkpoints\n```\n\n### 4 - Run!\nOnce your setup is complete, running tests is as simple as running `test.py`.\n\nUsage:\n\n```\nusage: test.py [-h]\n\npositional arguments:\n              The name of the dataset to perform tests on.Choose among\n              `mnist`, `cifar10`, `ucsd-ped2`, `shanghaitech`\n\noptional arguments:\n  -h, --help  show this help message and exit\n```\n\nExample:\n```\npython test.py ucsd-ped2\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faimagelab%2Fnovelty-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faimagelab%2Fnovelty-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faimagelab%2Fnovelty-detection/lists"}