{"id":22068848,"url":"https://xk-huang.github.io/segment-caption-anything/","last_synced_at":"2025-07-24T07:31:16.248Z","repository":{"id":209436287,"uuid":"720069145","full_name":"xk-huang/segment-caption-anything","owner":"xk-huang","description":"[CVPR 24] The repository provides code for running inference and training for \"Segment and Caption Anything\" (SCA) , links for downloading the trained model checkpoints, and example notebooks / gradio demo that show how to use the model. ","archived":false,"fork":false,"pushed_at":"2024-08-23T22:54:27.000Z","size":82765,"stargazers_count":176,"open_issues_count":1,"forks_count":5,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-08-23T23:51:01.787Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://xk-huang.github.io/segment-caption-anything/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xk-huang.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":"2023-11-17T14:10:41.000Z","updated_at":"2024-08-22T23:25:57.000Z","dependencies_parsed_at":"2024-06-19T03:02:14.620Z","dependency_job_id":null,"html_url":"https://github.com/xk-huang/segment-caption-anything","commit_stats":null,"previous_names":["xk-huang/segment-caption-anything"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xk-huang%2Fsegment-caption-anything","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xk-huang%2Fsegment-caption-anything/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xk-huang%2Fsegment-caption-anything/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xk-huang%2Fsegment-caption-anything/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xk-huang","download_url":"https://codeload.github.com/xk-huang/segment-caption-anything/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227421350,"owners_count":17775010,"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":"2024-11-30T20:04:25.407Z","updated_at":"2024-11-30T20:07:10.066Z","avatar_url":"https://github.com/xk-huang.png","language":"Python","funding_links":[],"categories":["Paper List"],"sub_categories":["Follow-up Papers"],"readme":"# Segment and Caption Anything\n\nThe repository contains the official implementation of \"Segment and Caption Anything\"\n\n[Project Page](https://xk-huang.github.io/segment-caption-anything), [Paper](https://arxiv.org/abs/2312.00869)\n\n![teaser](./docs/teaser-github.svg)\n\ntl;dr\n1. Despite the absence of semantic labels in the training data, SAM implies high-level semantics sufficient for captioning. \n2. SCA (b) is a lightweight augmentation of SAM (a) with the ability to generate regional captions.\n3. On top of SAM architecture, we add a fixed pre-trained language mode, and a optimizable lightweight hybrid feature mixture whose training is cheap and scalable.\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cimg src=\"./docs/anything-mode-00.png.jpg\" alt=\"anything-mode-00\"\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003cimg src=\"./docs/anything-mode-03.png.jpg\" alt=\"anything-mode-01\"\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cimg src=\"./docs/anything-mode-01.png.jpg\" alt=\"anything-mode-02\"\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003cimg src=\"./docs/anything-mode-02.png.jpg\" alt=\"anything-mode-03\"\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\nNews\n\n- [01/31/2024] Update the [paper](https://xk-huang.github.io/segment-caption-anything/files/segment-caption-anything.013124.pdf) and the [supp](https://xk-huang.github.io/segment-caption-anything/files/segment-caption-anything-supp.013124.pdf). Release code v0.0.2: bump transformers to 4.36.2, support mistral series, phi-2, zephyr; add experiments about SAM+Image Captioner+[V-CoT](https://github.com/ttengwang/Caption-Anything), and more. \n- [12/05/2023] Release paper, code v0.0.1, and project page!\n\n## Environment Preparation\n\nPlease check [docs/ENV.md](docs/ENV.md).\n\n\n## Model Zoo\n\nPlease check [docs/MODEL_ZOO.md](docs/MODEL_ZOO.md)\n\n\n## Gradio Demo\n\nPlease check [docs/DEMO.md](docs/DEMO.md)\n\n\n## Running Training and Inference\n\nPlease check [docs/USAGE.md](docs/USAGE.md).\n\n\n## Experiments and Evaluation\n\nPlease check [docs/EVAL.md](docs/EVAL.md)\n\n## License\n\nThe trained weights are licensed under the [Apache 2.0 license](https://github.com/xk-huang/segment-caption-anything/blob/1c810bfcfeb3b95cd4b1f502f8f30c46333d58b8/LICENSE).\n\n## Acknowledgement\n\nDeeply appreciate these wonderful open source projects: [transformers](https://github.com/huggingface/transformers), [accelerate](https://github.com/huggingface/accelerate), [deepspeed](https://github.com/microsoft/DeepSpeed), [detectron2](https://github.com/facebookresearch/detectron2), [hydra](https://github.com/facebookresearch/hydra), [timm](https://github.com/huggingface/pytorch-image-models), [gradio](https://github.com/gradio-app/gradio).\n\n## Citation\n\nIf you find this repository useful, please consider giving a star ⭐ and citation 🦖:\n\n```\n@inproceedings{huang2024segment,\n  title={Segment and caption anything},\n  author={Huang, Xiaoke and Wang, Jianfeng and Tang, Yansong and Zhang, Zheng and Hu, Han and Lu, Jiwen and Wang, Lijuan and Liu, Zicheng},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages={13405--13417},\n  year={2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/xk-huang.github.io%2Fsegment-caption-anything%2F","html_url":"https://awesome.ecosyste.ms/projects/xk-huang.github.io%2Fsegment-caption-anything%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/xk-huang.github.io%2Fsegment-caption-anything%2F/lists"}