{"id":18710476,"url":"https://github.com/vision-cair/cizslv2","last_synced_at":"2025-04-12T11:33:10.206Z","repository":{"id":113283910,"uuid":"298228822","full_name":"Vision-CAIR/CIZSLv2","owner":"Vision-CAIR","description":"CIZSL++: Creativity Inspired Generative Zero-Shot Learning. T-PAMI under review.","archived":false,"fork":false,"pushed_at":"2021-02-08T07:10:01.000Z","size":14513,"stargazers_count":6,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-26T06:11:40.574Z","etag":null,"topics":["attributes","creativity","generative-models","unseen-classes-understanding","vision-and-language","zero-shot-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Vision-CAIR.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":"2020-09-24T09:19:16.000Z","updated_at":"2024-01-23T13:55:03.000Z","dependencies_parsed_at":"2024-01-07T17:10:56.591Z","dependency_job_id":"e418c04a-b99d-4e48-ba36-164592356f6e","html_url":"https://github.com/Vision-CAIR/CIZSLv2","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/Vision-CAIR%2FCIZSLv2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vision-CAIR%2FCIZSLv2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vision-CAIR%2FCIZSLv2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vision-CAIR%2FCIZSLv2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vision-CAIR","download_url":"https://codeload.github.com/Vision-CAIR/CIZSLv2/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248560077,"owners_count":21124590,"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":["attributes","creativity","generative-models","unseen-classes-understanding","vision-and-language","zero-shot-learning"],"created_at":"2024-11-07T12:34:17.956Z","updated_at":"2025-04-12T11:33:10.188Z","avatar_url":"https://github.com/Vision-CAIR.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CIZSLv2\nCIZSL++: Creativity Inspired Generative Zero-shot Learning, Mohamed Elhoseiny, Kai Yi, Mohamed Elfeki, Arxiv, 2020 \n\n# Requirements\nPython 3.6\n\nPytorch 1.6\n\nsklearn, scipy, matplotlib, numpy, random, copy\n\n# Processed Feature Data \nYou can download the text-based dataset at [dataset CUBird and NABird](https://www.dropbox.com/s/9qovr86kgogkl6r/CUB_NAB_Data.zip). For attribute-based data, you can access to [here](https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/research/zero-shot-learning/zero-shot-learning-the-good-the-bad-and-the-ugly). \n\nPlease put the uncompressed data to the folder \"data\".\n\n# Reproduce CIZSLv2 Best Model\n```\npython train_cizslv2.py --dataset 'CUB' --splitmode 'easy' --creativity_weight 1  --exp_name 'cizslv2'              \npython train_cizslv2.py --dataset 'CUB' --splitmode 'hard' --creativity_weight 0.1  --exp_name 'cizslv2'                \npython train_cizslv2.py --dataset 'NAB' --splitmode 'easy' --creativity_weight 0.001  --exp_name 'cizslv2'              \npython train_cizslv2.py --dataset 'NAB' --splitmode 'hard' --creativity_weight 1  --exp_name 'cizslv2'\n```        \n\n# Reference\n- Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng and Ahmed Elgammal \"A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts\", CVPR, 2018\n- Mohamed Elhoseiny, Mohamed Elfeki, Creativity Inspired Zero Shot Learning, Thirty-sixth International Conference on Computer Vision (ICCV), 2019\n\nIf you find this code is useful, please cite:\n\n```\n@article{elhoseiny2021cizsl++,\n  title={CIZSL++: Creativity Inspired Generative Zero-Shot Learning},\n  author={Elhoseiny, Mohamed and Yi, Kai and Elfeki, Mohamed},\n  journal={arXiv preprint arXiv:2101.00173},\n  year={2021}\n}\n```\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvision-cair%2Fcizslv2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvision-cair%2Fcizslv2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvision-cair%2Fcizslv2/lists"}