{"id":21319852,"url":"https://github.com/jason-cs18/chameleon","last_synced_at":"2026-03-19T19:53:21.200Z","repository":{"id":90320112,"uuid":"433060316","full_name":"Jason-cs18/Chameleon","owner":"Jason-cs18","description":"Chameleon: An efficient continuous adaptation framework based on NVIDIA TAO.","archived":false,"fork":false,"pushed_at":"2021-11-29T14:21:18.000Z","size":2,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-05-18T17:58:45.957Z","etag":null,"topics":["continuous-learning","domain-adaptation","model-selection","nvidia-tao-toolkit"],"latest_commit_sha":null,"homepage":"","language":null,"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/Jason-cs18.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":"2021-11-29T13:48:19.000Z","updated_at":"2023-05-30T09:53:50.000Z","dependencies_parsed_at":"2024-01-25T19:14:52.582Z","dependency_job_id":null,"html_url":"https://github.com/Jason-cs18/Chameleon","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/Jason-cs18%2FChameleon","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jason-cs18%2FChameleon/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jason-cs18%2FChameleon/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jason-cs18%2FChameleon/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Jason-cs18","download_url":"https://codeload.github.com/Jason-cs18/Chameleon/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243801205,"owners_count":20350103,"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":["continuous-learning","domain-adaptation","model-selection","nvidia-tao-toolkit"],"created_at":"2024-11-21T19:44:30.653Z","updated_at":"2025-10-05T15:37:11.424Z","avatar_url":"https://github.com/Jason-cs18.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Chameleon\nChameleon is an efficient continuous adaptation framework based on [NVIDIA TAO](https://developer.nvidia.com/zh-cn/tao-toolkit-get-started). To bridge the gap between one-time domain adaptation and continuous learning, we propose Chameleon, which updates models on new data (labeled or unlabeled) via **existing domain adaptation techniques** and select the suitable model to recovery accuracy through **adaptive model selection methods**. In implementation, we provide different adaptation strategies and optimization techniques for different visual tasks (object detection, segmentation, tracking and SLAM). In the end, we summary existing common optimization techniques (GPU sharing, ...).\n## 1. Installation (TAO and Docker)\n## 2. Scenarios (adaptation strategies and optimization techniques)\n### Object Detection\n### Image Segmentation\n### Visual Tracking\n### SLAM (in progress)\n## 3. Common optimization techniques\n- GPU Sharing between training and inference: [Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers. Published in _NSDI'22_.](https://www.microsoft.com/en-us/research/publication/ekya-continuous-learning-of-video-analytics-models-on-edge-compute-servers-2/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjason-cs18%2Fchameleon","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjason-cs18%2Fchameleon","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjason-cs18%2Fchameleon/lists"}