{"id":20111837,"url":"https://github.com/lufficc/dpnet","last_synced_at":"2025-05-06T11:31:21.704Z","repository":{"id":107996542,"uuid":"200071252","full_name":"lufficc/DPNet","owner":"lufficc","description":"Data Priming Network for Automatic Check-Out - ACMMM 2019","archived":false,"fork":false,"pushed_at":"2019-09-09T14:35:50.000Z","size":2078,"stargazers_count":26,"open_issues_count":2,"forks_count":2,"subscribers_count":8,"default_branch":"master","last_synced_at":"2023-10-20T21:20:28.652Z","etag":null,"topics":["acmmm2019","dpnet","pytorch"],"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/lufficc.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}},"created_at":"2019-08-01T15:01:10.000Z","updated_at":"2022-10-10T15:01:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"384f2b56-cfba-4d41-80a7-b9257c3f33d8","html_url":"https://github.com/lufficc/DPNet","commit_stats":null,"previous_names":[],"tags_count":1,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lufficc%2FDPNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lufficc%2FDPNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lufficc%2FDPNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lufficc%2FDPNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lufficc","download_url":"https://codeload.github.com/lufficc/DPNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224499851,"owners_count":17321605,"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":["acmmm2019","dpnet","pytorch"],"created_at":"2024-11-13T18:17:53.509Z","updated_at":"2024-11-13T18:17:54.163Z","avatar_url":"https://github.com/lufficc.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data Priming Network for Automatic Check-Out\n\nIntroduction\n-----------------\nThis paper was accepted to ACM MM 2019.\n\nThis repository implements DPNet ([Data Priming Network for Automatic Check-Out](https://arxiv.org/abs/1904.04978)) using PyTorch 1.0.1 . This implementation is heavily influenced by the project [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark).\n\nWe propose a new data priming method\nto solve the domain adaptation problem. Specifically, we first use\npre-augmentation data priming, in which we remove distracting\nbackground from the training images using the coarse-to-fine strategy and select images with realistic view angles by the pose pruning\nmethod. In the post-augmentation step, we train a data priming\nnetwork using detection and counting collaborative learning, and\nselect more reliable images from testing data to fine-tune the final\nvisual item tallying network.\n\n![DPNet](DPNet.png)\n\n## Code\n\nSource code and more details are available [here](https://isrc.iscas.ac.cn/gitlab/research/acm-mm-2019-ACO).\n\n\n## Results\n\n![DPNet](results.png)\n\n|    level |      method        |   cAcc |  mCIoU |  ACD | mCCD |  mAP50 |   mmAP |\n|     ---: |               ---: |   ---: |   ---: | ---: | ---: |   ---: |   ---: |\n|     easy | Syn+Render (DPNet) | 90.32% | 97.87% | 0.15 | 0.02 |  98.6% | 83.07% |\n|   medium | Syn+Render (DPNet) | 80.68% | 97.38% | 0.32 | 0.03 | 98.07% | 77.25% |\n|     hard | Syn+Render (DPNet) | 70.76% | 97.04% | 0.53 | 0.03 | 97.76% | 74.95% |\n| averaged | Syn+Render (DPNet) | 80.51% | 97.33% | 0.34 | 0.03 | 97.91% | 77.04% |\n\n## Model ZOO\n\n|    level |      method        |   cAcc |  model |\n|     ---: |               ---: |   ---: |   ---: |\n| averaged | Render (DPNet) | 77.91% | [download](https://github.com/lufficc/DPNet/releases/download/0.1/render_finetune.pth) |\n| averaged | Syn+Render (DPNet) | 80.51% | [download](https://github.com/lufficc/DPNet/releases/download/0.1/syn_render_finetune.pth) |\n\n\n## Citations\nPlease cite this project in your publications if it helps your research. \n```\n@inproceedings{li2019data,\n  title={Data Priming Network for Automatic Check-Out},\n  author={Li, Congcong and Du, Dawei and Zhang, Libo and Luo, Tiejian and Wu, Yanjun and Tian, Qi and Wen, Longyin and Lyu, Siwei},\n  booktitle={2019 ACM Multimedia Conference on Multimedia Conference},\n  year={2019},\n  organization={ACM}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flufficc%2Fdpnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flufficc%2Fdpnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flufficc%2Fdpnet/lists"}