{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/feature-generating-networks-for-zero-shot","title":"Feature Generating Networks for Zero-Shot Learning","arxiv_id":"1712.00981","date":"2017-12-04","proceeding":"CVPR 2018 6","authors":["Yongqin Xian","Tobias Lorenz","Bernt Schiele","Zeynep Akata"],"abstract":"Suffering from the extreme training data imbalance between seen and unseen\nclasses, most of existing state-of-the-art approaches fail to achieve\nsatisfactory results for the challenging generalized zero-shot learning task.\nTo circumvent the need for labeled examples of unseen classes, we propose a\nnovel generative adversarial network (GAN) that synthesizes CNN features\nconditioned on class-level semantic information, offering a shortcut directly\nfrom a semantic descriptor of a class to a class-conditional feature\ndistribution. Our proposed approach, pairing a Wasserstein GAN with a\nclassification loss, is able to generate sufficiently discriminative CNN\nfeatures to train softmax classifiers or any multimodal embedding method. Our\nexperimental results demonstrate a significant boost in accuracy over the state\nof the art on five challenging datasets -- CUB, FLO, SUN, AWA and ImageNet --\nin both the zero-shot learning and generalized zero-shot learning settings.","url_abs":"http://arxiv.org/abs/1712.00981v2","url_pdf":"http://arxiv.org/pdf/1712.00981v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"feature-generating-networks-for-zero-shot","repo_url":"https://github.com/Abhipanda4/Feature-Generating-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"feature-generating-networks-for-zero-shot","repo_url":"https://github.com/CristianoPatricio/zsl-methods","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"feature-generating-networks-for-zero-shot","repo_url":"https://github.com/akku1506/Feature-Generating-Networks-for-ZSL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"feature-generating-networks-for-zero-shot","repo_url":"https://github.com/mkara44/f-clswgan_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"generalized-zero-shot-learning","task_name":"Generalized Zero-Shot Learning"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-zero-shot-learning-on-sun","task":"Generalized Zero-Shot Learning","dataset":"SUN Attribute","model":"f-CLSWGAN","rank_in_archive_order":7,"of":9,"metrics":{"Harmonic mean":"39.4"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-cub-200-2011","task":"Zero-Shot Learning","dataset":"CUB-200-2011","model":"f-CLSWGAN","rank_in_archive_order":12,"of":14,"metrics":{"average top-1 classification accuracy":"57.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-sun-attribute","task":"Zero-Shot Learning","dataset":"SUN Attribute","model":"f-CLSWGAN","rank_in_archive_order":8,"of":9,"metrics":{"average top-1 classification accuracy":"60.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.00981","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}