{"id":19279960,"url":"https://github.com/showlab/efficient-cls","last_synced_at":"2025-04-22T00:33:13.599Z","repository":{"id":107917978,"uuid":"498566857","full_name":"showlab/Efficient-CLS","owner":"showlab","description":"[ICCV 2023] Label-Efficient Online Continual Object Detection in Streaming Video","archived":false,"fork":false,"pushed_at":"2024-01-08T09:13:37.000Z","size":4760,"stargazers_count":19,"open_issues_count":3,"forks_count":2,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-01T17:24:56.401Z","etag":null,"topics":["continual-learning","label-efficient","object-detection","online-continual-learning","video-streaming"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/showlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2022-06-01T02:37:33.000Z","updated_at":"2025-02-17T20:25:32.000Z","dependencies_parsed_at":"2023-12-22T16:50:30.839Z","dependency_job_id":"eb295b13-f880-4676-9625-46137730e2b2","html_url":"https://github.com/showlab/Efficient-CLS","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/showlab%2FEfficient-CLS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FEfficient-CLS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FEfficient-CLS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/showlab%2FEfficient-CLS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/showlab","download_url":"https://codeload.github.com/showlab/Efficient-CLS/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250158021,"owners_count":21384334,"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":["continual-learning","label-efficient","object-detection","online-continual-learning","video-streaming"],"created_at":"2024-11-09T21:16:14.336Z","updated_at":"2025-04-22T00:33:12.999Z","avatar_url":"https://github.com/showlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Effcient-CLS\n\nThis repository is the official implementation of the following paper:\n\n**[Label-Efficient Online Continual Object Detection in Streaming Video](https://arxiv.org/abs/2206.00309)**\n\u003cbr/\u003e\n[Jay Zhangjie Wu](https://zhangjiewu.github.io/), \n[David Junhao Zhang](https://junhaozhang98.github.io/), \n[Wynne Hsu](https://www.comp.nus.edu.sg/~whsu/), \n[Mengmi Zhang](https://a0091624.wixsite.com/deepneurocognition-1), \n[Mike Zheng Shou](https://sites.google.com/view/showlab)\n\u003cbr/\u003e\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"assets/overview.png\" width=\"1080px\"/\u003e  \n\u003c/p\u003e\n\n\n## Setup\n\n### Installation\n\nClone the repository and install the dependencies:\n\n```bash\ngit clone https://github.com/showlab/Efficient-CLS.git\npip install Efficient-CLS/requirements.txt\npython -m pip install -e Efficient-CLS\n```\n\n### Datasets\n\nWe provide the processed datasets in the Google Drive ([OAK](https://drive.google.com/file/d/1TewbRDPhutTDHT5vl_0hE30hotZqcffV/view?usp=sharing), [EgoObjects](https://drive.google.com/file/d/10d0XSS5G_HW4P8ptVh7k-PT50Phmb3XN/view?usp=sharing)). Download the datasets and modify the `DATA_DIR` in `configs/efficient_cls.yaml` to the corresponding directory.\n\n### Pretrained Models\n\nWe use Faster R-CNN on PASCAL VOC object detection. Run the following commands to download the pretrained weights in [Detectron2 Model Zoo](https://github.com/facebookresearch/detectron2/blob/main/MODEL_ZOO.md#cityscapes--pascal-voc-baselines). \n\n```bash\nmkdir weights \u0026\u0026 wget https://dl.fbaipublicfiles.com/detectron2/PascalVOC-Detection/faster_rcnn_R_50_C4/142202221/model_final_b1acc2.pkl -P weights/\n```\n\n## Usage\n\nTo start training, run this:\n```bash\n# E.g., run experiment on OAK dataset at 4/16 annotation cost, with 12/16 unlabeled data trained with pseudo labels.\npython train.py --exp=train --dataset=oak --num_oracle=4 --num_pseudo=12 --replay_size=16\n```\n\n## Shoutouts\n\n- This code builds on [detectron2](https://github.com/facebookresearch/detectron2). Thanks for opensourcing!\n- Thanks the contributors of [OAK](https://oakdata.github.io/) and [EgoObjects](https://ai.meta.com/datasets/egoobjects-downloads/) for sharing the datasets!\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshowlab%2Fefficient-cls","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshowlab%2Fefficient-cls","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshowlab%2Fefficient-cls/lists"}