{"id":13613328,"url":"https://github.com/lyakaap/ISC21-Descriptor-Track-1st","last_synced_at":"2025-04-13T15:32:57.943Z","repository":{"id":42200100,"uuid":"381269085","full_name":"lyakaap/ISC21-Descriptor-Track-1st","owner":"lyakaap","description":"The 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track.","archived":false,"fork":false,"pushed_at":"2023-11-08T03:40:28.000Z","size":25424,"stargazers_count":134,"open_issues_count":5,"forks_count":19,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-11-07T21:42:00.673Z","etag":null,"topics":[],"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/lyakaap.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}},"created_at":"2021-06-29T06:57:34.000Z","updated_at":"2024-11-02T10:41:41.000Z","dependencies_parsed_at":"2024-01-12T19:47:33.487Z","dependency_job_id":"f5570181-fff9-406b-bea0-024421b42c2a","html_url":"https://github.com/lyakaap/ISC21-Descriptor-Track-1st","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyakaap%2FISC21-Descriptor-Track-1st","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyakaap%2FISC21-Descriptor-Track-1st/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyakaap%2FISC21-Descriptor-Track-1st/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lyakaap%2FISC21-Descriptor-Track-1st/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lyakaap","download_url":"https://codeload.github.com/lyakaap/ISC21-Descriptor-Track-1st/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248736082,"owners_count":21153531,"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":"2024-08-01T20:00:44.395Z","updated_at":"2025-04-13T15:32:57.652Z","avatar_url":"https://github.com/lyakaap.png","language":"Python","funding_links":[],"categories":["Python","其他_机器视觉"],"sub_categories":["网络服务_其他"],"readme":"# ISC21-Descriptor-Track-1st\n\nThe 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track.\n\nYou can check our solution tech report from: [Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection](https://arxiv.org/abs/2112.04323)\n\nMain features:\n- The weights of the competition winning models are publicly available and easy to use.\n- Without any fine-tuning or something, our models work well with image/video copy detection, image retrieval, and so on.\n  - In video copy detection task, it is reported that our model has the best result among recent frame feature extractor, despite with the smallest feature dimensionality (ref: https://github.com/alipay/VCSL).\n\n## Installation\n\n```\npip install git+https://github.com/lyakaap/ISC21-Descriptor-Track-1st\n```\n\n## Usage\n\n```python\nimport requests\nimport torch\nfrom PIL import Image\n\nfrom isc_feature_extractor import create_model\n\nrecommended_weight_name = 'isc_ft_v107'\nmodel, preprocessor = create_model(weight_name=recommended_weight_name, device='cpu')\n\nurl = \"http://images.cocodataset.org/val2017/000000039769.jpg\"\nimage = Image.open(requests.get(url, stream=True).raw)\nx = preprocessor(image).unsqueeze(0)\n\ny = model(x)\nprint(y.shape)  # =\u003e torch.Size([1, 256])\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flyakaap%2FISC21-Descriptor-Track-1st","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flyakaap%2FISC21-Descriptor-Track-1st","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flyakaap%2FISC21-Descriptor-Track-1st/lists"}