{"id":20962211,"url":"https://github.com/lartpang/zoomnet","last_synced_at":"2025-09-19T02:32:10.921Z","repository":{"id":41873534,"uuid":"465136063","full_name":"lartpang/ZoomNet","owner":"lartpang","description":"Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection, CVPR 2022","archived":false,"fork":false,"pushed_at":"2023-11-01T07:04:22.000Z","size":2445,"stargazers_count":129,"open_issues_count":0,"forks_count":21,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-12-28T23:32:37.194Z","etag":null,"topics":["camouflaged-object-detection","cod","codeforpaper","cvpr","cvpr2022","paper","papercode","python","pytorch","rgbcod","rgbsod","saliency-detection","salient-object-detection","sod"],"latest_commit_sha":null,"homepage":"https://lartpang.github.io/docs/zoomnet.html","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/lartpang.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}},"created_at":"2022-03-02T02:58:21.000Z","updated_at":"2024-12-20T10:39:28.000Z","dependencies_parsed_at":"2022-09-24T07:41:16.031Z","dependency_job_id":"f98068e5-feaa-4cba-9a5a-9b02214e040b","html_url":"https://github.com/lartpang/ZoomNet","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lartpang%2FZoomNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lartpang%2FZoomNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lartpang%2FZoomNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lartpang%2FZoomNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lartpang","download_url":"https://codeload.github.com/lartpang/ZoomNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233546475,"owners_count":18692226,"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":["camouflaged-object-detection","cod","codeforpaper","cvpr","cvpr2022","paper","papercode","python","pytorch","rgbcod","rgbsod","saliency-detection","salient-object-detection","sod"],"created_at":"2024-11-19T02:24:31.619Z","updated_at":"2025-09-19T02:32:05.336Z","avatar_url":"https://github.com/lartpang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# (CVPR 2022) Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection\n\n[![license: mit](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n![LAST COMMIT](https://img.shields.io/github/last-commit/lartpang/ZoomNet?style=flat-square)\n![ISSUES](https://img.shields.io/github/issues/lartpang/ZoomNet?style=flat-square)\n![STARS](https://img.shields.io/github/stars/lartpang/ZoomNet?style=flat-square)\n[![ARXIV PAPER](https://img.shields.io/badge/Arxiv-Paper-red?style=flat-square)](https://arxiv.org/abs/2203.02688)\n[![ARXIV PAPER](https://img.shields.io/badge/Github-Paper-red?style=flat-square)](https://github.com/lartpang/ZoomNet/releases/download/v0.0.1/zoomnet-arxiv.pdf)\n\n```\n@inproceedings{ZoomNet-CVPR2022,\n\ttitle     = {Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection},\n\tauthor    = {Pang, Youwei and Zhao, Xiaoqi and Xiang, Tian-Zhu and Zhang, Lihe and Lu, Huchuan},\n\tbooktitle = CVPR,\n\tyear      = {2022}\n}\n```\n\n**Extensions to the conference version can be found: \u003chttps://github.com/lartpang/ZoomNeXt\u003e.**\n\n## Changelog\n\n* 2022-3-16\n    - Add the link of the method prediction maps of Table 1 in our paper.\n* 2022-03-08\n    - Add the link of arxiv version.\n* 2022-03-07\n    - Add the link of paper.\n* 2022-03-05:\n    - Update weights and results links.\n    - Fixed some bugs.\n    - Update dataset links.\n    - Update bibtex info.\n* 2022-03-04:\n    - Initialize the repository.\n    - Add the model and configuration file for SOD.\n\n## Usage\n\n### Dependencies\n\nSome core dependencies:\n\n- timm == 0.4.12\n- torch == 1.8.1\n- [pysodmetrics](https://github.com/lartpang/PySODMetrics) == 1.2.4 # for evaluating results\n\nMore details can be found in \u003c./requirements.txt\u003e\n\n### Datasets\n\nMore details can be found at:\n- COD Datasets: \u003chttps://github.com/lartpang/awesome-segmentation-saliency-dataset#camouflaged-object-detection-cod\u003e\n- SOD Datasets: \u003chttps://github.com/lartpang/awesome-segmentation-saliency-dataset#rgb-saliency\u003e\n\n### Training\n\nYou can use our default configuration, like this:\n\n```shell\n$ python main.py --model-name=ZoomNet --config=configs/zoomnet/zoomnet.py --datasets-info ./configs/_base_/dataset/dataset_configs.json --info demo\n```\n\nor use our launcher script to start the one command in `commands.txt` on GPU 1:\n\n```shell\n$ python tools/run_it.py --interpreter 'abs_path' --cmd-pool tools/commands.txt  --gpu-pool 1 --verbose --max-workers 1\n```\n\nIf you want to launch multiple commands, you can use it like this:\n\n1. Add your commands into the `tools/commands.txt`.\n2. `python tools/run_it.py --interpreter 'abs_path' --cmd-pool tools/commands.txt --gpu-pool \u003cgpu indices\u003e --verbose --max-workers max_workers`\n\n**NOTE**:\n\n- `abs_path`: the absolute path of your python interpreter\n- `max_workers`: the maximum number of tasks to start simultaneously.\n\n### Testing\n\n| Task | Weights                                                                                                                           | Results                                                                                                       |\n| ---- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |\n| COD  | [GitHub Release Link](https://github.com/lartpang/ZoomNet/releases/download/v0.0.1/cod_zoomnet_r50_bs8_e40_2022-03-04.pth)        | [GitHub Release Link](https://github.com/lartpang/ZoomNet/releases/download/v0.0.1/CVPR-2022-ZoomNet-COD.zip) |\n| SOD  | [GitHub Release Link](https://github.com/lartpang/ZoomNet/releases/download/v0.0.1/sod_zoomnet_r50_bs22_e50_2022-03-04_fixed.pth) | [GitHub Release Link](https://github.com/lartpang/ZoomNet/releases/download/v0.0.1/CVPR-2022-ZoomNet-SOD.zip) |\n\nFor ease of use, we create a `test.py` script and a use case in the form of a shell script `test.sh`.\n\n```shell\n$ sudo chmod +x ./test.sh\n$ ./test.sh 0  # on gpu 0\n```\n\n### Method Comparisons\n\n- The prediction maps corresponding to the methods in Table 1 of our paper:\n    - Baidu Pan: \u003chttps://pan.baidu.com/s/1dLMqa4tix1gdBN1uWrCPbQ\u003e Code: yxy9\n- PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection\n    - \u003chttps://github.com/lartpang/PySODEvalToolkit\u003e\n\n## Paper Details\n\n### Method Detials\n\n![](./assets/feat.png)\n\n![](./assets/net.png)\n\n### Comparison\n\n#### Camouflaged Object Detection\n\n![](./assets/cod_vis.png)\n\n![](./assets/cod_cmp.png)\n\n![](./assets/cod_fmpr.png)\n\n#### Salient Object Detection\n\n![](./assets/sod_cmp.png)\n\n![](./assets/sod_fmpr.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flartpang%2Fzoomnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flartpang%2Fzoomnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flartpang%2Fzoomnet/lists"}