{"id":19756430,"url":"https://github.com/zhaoxin94/fsac","last_synced_at":"2026-03-02T09:33:16.020Z","repository":{"id":134684957,"uuid":"519410801","full_name":"zhaoxin94/FSAC","owner":"zhaoxin94","description":null,"archived":false,"fork":false,"pushed_at":"2021-12-16T05:44:44.000Z","size":8039,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-28T09:11:37.382Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":false,"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/zhaoxin94.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":"2022-07-30T03:43:58.000Z","updated_at":"2022-04-04T10:03:34.000Z","dependencies_parsed_at":"2023-03-30T19:56:50.912Z","dependency_job_id":null,"html_url":"https://github.com/zhaoxin94/FSAC","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zhaoxin94/FSAC","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhaoxin94%2FFSAC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhaoxin94%2FFSAC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhaoxin94%2FFSAC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhaoxin94%2FFSAC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zhaoxin94","download_url":"https://codeload.github.com/zhaoxin94/FSAC/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhaoxin94%2FFSAC/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29997213,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T01:47:34.672Z","status":"online","status_checked_at":"2026-03-02T02:00:07.342Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2024-11-12T03:15:57.108Z","updated_at":"2026-03-02T09:33:15.987Z","avatar_url":"https://github.com/zhaoxin94.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection\n\n## Main requirements\ntorch \u003e= 1.0\n\ntorchvision \u003e= 0.2.0\n\nPython 3\n\n## Environmental settings\nThis repository is developed using python 3.6.12 on Ubuntu 16.04.5 LTS. The CUDA and pytorch version is 11.2 and 1.7.1. We use one NVIDIA 3090 GPU card for training and testing.\n\n## Dataset\nPASCAL VOC, Watercolor, Cityscapes, Foggycityscapes -\u003e Please follow the instructions in [[Link](https://github.com/VisionLearningGroup/DA_Detection)] to prepare the datasets.\n\nDaytime-Sunny, Dusk-Rainy, and Night-Rainy -\u003e Dataset preparation instruction link [[Link](https://github.com/AmingWu/VDD-DAOD)].\n\n## Code\nFaster R-CNN -\u003e Thanks for jwyang [[Link](https://github.com/jwyang/faster-rcnn.pytorch/tree/pytorch-1.0)]; Fourier Domain Adaptation -\u003e Thanks for Yanchao Yang [[Link](https://github.com/YanchaoYang/FDA)].\n\nOur Augmentation (Mix+Replace+Extend+Disorder).\n\n## Train\nTo train a faster R-CNN model with vgg16 on pascal_voc:\n```\nCUDA_VISIBLE_DEVICES=$GPU_ID python trainval_net.py --dataset pascal_voc --net vgg16 --bs 1 --cuda\n```\n\nAnd you need to add augmentated data in the loadpath by creating a new dataset_name variable.\n\n## Test\nTo test:\n```\npython test_net.py --dataset pascal_voc --net vgg16 --modelpath your modelpath --cuda\n```\n\n## Augmentation\nDaytime-Sunny -\u003e Dusk-Rainy\n![shapenet_illuminants](image/aug1.png)\n\nDaytime-Sunny -\u003e Night-Rainy\n![shapenet_illuminants](image/aug2.png)\n\n## Result\n![shapenet_illuminants](image/result.png)\n\nResults on adaptation from Cityscapes to FoggyCityscapes. ‘prsn’, ‘mcycl’, and ‘bcycl’ separately denote ‘person’, ‘motorcycle’, and ‘bicycle’ category.\n\n![shapenet_illuminants](image/table2.png)\n\nResults on adaptation from Daytime-sunny to Duskrainy. Here, we directly run the released codes of the compared methods to obtain the results.\n\n![shapenet_illuminants](image/table3.png)\n\nResults on Daytime-sunny → Night-rainy.\n\n![shapenet_illuminants](image/table4.png)\n\nResults on the compound target domain.\n\n![shapenet_illuminants](image/table5.png)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhaoxin94%2Ffsac","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzhaoxin94%2Ffsac","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhaoxin94%2Ffsac/lists"}