{"id":13422288,"url":"https://github.com/edgarschnfld/CADA-VAE-PyTorch","last_synced_at":"2025-03-15T11:31:37.788Z","repository":{"id":37594454,"uuid":"164482552","full_name":"edgarschnfld/CADA-VAE-PyTorch","owner":"edgarschnfld","description":"Official implementation of the paper \"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders\" (CVPR 2019)","archived":false,"fork":false,"pushed_at":"2023-07-06T21:26:21.000Z","size":41585,"stargazers_count":281,"open_issues_count":8,"forks_count":58,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-07-31T23:45:09.103Z","etag":null,"topics":["few-shot-learning","generalized-zero-shot-learning","vae","variational-autoencoder","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/edgarschnfld.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}},"created_at":"2019-01-07T19:35:18.000Z","updated_at":"2024-05-22T09:37:49.000Z","dependencies_parsed_at":"2024-01-16T00:18:47.406Z","dependency_job_id":"aec7cc2b-e3f7-4f1d-a660-6a365eac643f","html_url":"https://github.com/edgarschnfld/CADA-VAE-PyTorch","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/edgarschnfld%2FCADA-VAE-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edgarschnfld%2FCADA-VAE-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edgarschnfld%2FCADA-VAE-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edgarschnfld%2FCADA-VAE-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/edgarschnfld","download_url":"https://codeload.github.com/edgarschnfld/CADA-VAE-PyTorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221572086,"owners_count":16845580,"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":["few-shot-learning","generalized-zero-shot-learning","vae","variational-autoencoder","zero-shot-learning"],"created_at":"2024-07-30T23:00:41.117Z","updated_at":"2024-10-26T19:32:49.275Z","avatar_url":"https://github.com/edgarschnfld.png","language":"Python","funding_links":[],"categories":["Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders. CVPR 2019"],"sub_categories":["Abstract"],"readme":"# CADA-VAE\nOriginal PyTorch implementation of \"Generalized Zero-and Few-Shot Learning via Aligned Variational Autoencoders\" (CVPR 2019).\n\nPaper: https://arxiv.org/pdf/1812.01784.pdf\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"600\" src=\"Model.jpg\"\u003e\n\u003c/p\u003e\n\u003cp align=\"justify\"\u003e\n  \n### Requirements\nThe code was implemented using Python 3.5.6 and the following packages:\n```\ntorch==0.4.1\nnumpy==1.14.3\nscipy==1.1.0\nscikit_learn==0.20.3\nnetworkx==1.11\n```\nUsing Python 2 is not recommended.\n\n### Data\nDownload the following folder https://www.dropbox.com/sh/btoc495ytfbnbat/AAAaurkoKnnk0uV-swgF-gdSa?dl=0\nand put it in this repository.\nNext to the folder \"model\", there should be a folder \"data\".\n\n### Experiments\n\nTo run the experiments from the paper, navigate to the model folder and execute the following:\n```\npython single_experiment.py --dataset CUB --num_shots 0 --generalized True\n```\nThe choices for the input arguments are:\n```\ndatasets: CUB, SUN, AWA1, AWA2\nnum_shots: any number \ngeneralized: True, False\n```\nMore hyperparameters can be adjusted in the file single_experiment.py directly. The results vary by 1-2% between identical runs.\n\n### Citation\nIf you use this work please cite\n```\n@inproceedings{schonfeld2019generalized,\n  title={Generalized zero-and few-shot learning via aligned variational autoencoders},\n  author={Schonfeld, Edgar and Ebrahimi, Sayna and Sinha, Samarth and Darrell, Trevor and Akata, Zeynep},\n  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},\n  pages={8247--8255},\n  year={2019}\n}\n```\n### Contact \nFor questions or help, feel welcome to write an email to edgarschoenfeld@live.de\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedgarschnfld%2FCADA-VAE-PyTorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fedgarschnfld%2FCADA-VAE-PyTorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedgarschnfld%2FCADA-VAE-PyTorch/lists"}