{"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/attgan-facial-attribute-editing-by-only","title":"AttGAN: Facial Attribute Editing by Only Changing What You Want","arxiv_id":"1711.10678","date":"2017-11-29","proceeding":null,"authors":["Zhenliang He","WangMeng Zuo","Meina Kan","Shiguang Shan","Xilin Chen"],"abstract":"Facial attribute editing aims to manipulate single or multiple attributes of\na face image, i.e., to generate a new face with desired attributes while\npreserving other details. Recently, generative adversarial net (GAN) and\nencoder-decoder architecture are usually incorporated to handle this task with\npromising results. Based on the encoder-decoder architecture, facial attribute\nediting is achieved by decoding the latent representation of the given face\nconditioned on the desired attributes. Some existing methods attempt to\nestablish an attribute-independent latent representation for further attribute\nediting. However, such attribute-independent constraint on the latent\nrepresentation is excessive because it restricts the capacity of the latent\nrepresentation and may result in information loss, leading to over-smooth and\ndistorted generation. Instead of imposing constraints on the latent\nrepresentation, in this work we apply an attribute classification constraint to\nthe generated image to just guarantee the correct change of desired attributes,\ni.e., to \"change what you want\". Meanwhile, the reconstruction learning is\nintroduced to preserve attribute-excluding details, in other words, to \"only\nchange what you want\". Besides, the adversarial learning is employed for\nvisually realistic editing. These three components cooperate with each other\nforming an effective framework for high quality facial attribute editing,\nreferred as AttGAN. Furthermore, our method is also directly applicable for\nattribute intensity control and can be naturally extended for attribute style\nmanipulation. Experiments on CelebA dataset show that our method outperforms\nthe state-of-the-arts on realistic attribute editing with facial details well\npreserved.","url_abs":"http://arxiv.org/abs/1711.10678v3","url_pdf":"http://arxiv.org/pdf/1711.10678v3.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":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/LynnHo/AttGAN-Tensorflow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/Ash-Lee233/attgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/GarlandZhang/hairy_gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/LynnHo/AttGAN-Cartoon-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/elvisyjlin/AttGAN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/jaewon0314/attGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/kszu/UniGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/2023-MindSpore-1/ms-code-16/tree/main/AttGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/AttGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"attgan-facial-attribute-editing-by-only","repo_url":"https://github.com/mindspore-ai/models/blob/master/research/cv/AttGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.10678","atlas_url":"https://app.syntology.ai/?focus=1711.10678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10678"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LynnHo/AttGAN-Tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ash-Lee233/attgan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LynnHo/AttGAN-Cartoon-Tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/elvisyjlin/AttGAN-PyTorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-16/tree/main/AttGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/AttGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GarlandZhang/hairy_gan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaewon0314/attGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kszu/UniGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/blob/master/research/cv/AttGAN","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"07f34ea31c2d8492","entry":"parse","repo":"elvisyjlin/AttGAN-PyTorch","repo_kind":"listed","path":"test_multi.py","file_url":"https://github.com/elvisyjlin/AttGAN-PyTorch/blob/HEAD/test_multi.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07f34ea31c2d8492"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}