{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1712.00981","atlas_url":"https://app.syntology.ai/?focus=1712.00981","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1712.00981"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1712.00981\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1712.00981"},"call":"get_concepts_for_paper(arxiv_id=\"1712.00981\")"}],"by_repo":[{"repo":"Abhipanda4/Feature-Generating-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CristianoPatricio/zsl-methods","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.16173"],"harvested_for_calls":[{"arxiv_id":"2103.16173","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.16173"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.16173\")"}]},{"repo":"akku1506/Feature-Generating-Networks-for-ZSL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mkara44/f-clswgan_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a5c9457e8573f29fb8847fa0ace43f5103490ff6342f76cc697571612fe24c29","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}