{"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/image-to-image-translation-for-cross-domain","title":"Image-to-image translation for cross-domain disentanglement","arxiv_id":"1805.09730","date":"2018-05-24","proceeding":"NeurIPS 2018 12","authors":["Abel Gonzalez-Garcia","Joost Van de Weijer","Yoshua Bengio"],"abstract":"Deep image translation methods have recently shown excellent results,\noutputting high-quality images covering multiple modes of the data\ndistribution. There has also been increased interest in disentangling the\ninternal representations learned by deep methods to further improve their\nperformance and achieve a finer control. In this paper, we bridge these two\nobjectives and introduce the concept of cross-domain disentanglement. We aim to\nseparate the internal representation into three parts. The shared part contains\ninformation for both domains. The exclusive parts, on the other hand, contain\nonly factors of variation that are particular to each domain. We achieve this\nthrough bidirectional image translation based on Generative Adversarial\nNetworks and cross-domain autoencoders, a novel network component. Our model\noffers multiple advantages. We can output diverse samples covering multiple\nmodes of the distributions of both domains, perform domain-specific image\ntransfer and interpolation, and cross-domain retrieval without the need of\nlabeled data, only paired images. We compare our model to the state-of-the-art\nin multi-modal image translation and achieve better results for translation on\nchallenging datasets as well as for cross-domain retrieval on realistic\ndatasets.","url_abs":"http://arxiv.org/abs/1805.09730v3","url_pdf":"http://arxiv.org/pdf/1805.09730v3.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":"image-to-image-translation-for-cross-domain","repo_url":"https://github.com/agonzgarc/cross-domain-disen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.09730","atlas_url":"https://app.syntology.ai/?focus=1805.09730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09730"}},"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/agonzgarc/cross-domain-disen","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"a5d1f6fc5ff054d8","entry":"append_index","repo":"agonzgarc/cross-domain-disen","repo_kind":"official","path":"run_cross_domain_disen.py","file_url":"https://github.com/agonzgarc/cross-domain-disen/blob/HEAD/run_cross_domain_disen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a5d1f6fc5ff054d8"}},{"code_sha256_prefix":"8ba79ebda1e637b3","entry":"save_features","repo":"agonzgarc/cross-domain-disen","repo_kind":"official","path":"run_cross_domain_disen.py","file_url":"https://github.com/agonzgarc/cross-domain-disen/blob/HEAD/run_cross_domain_disen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8ba79ebda1e637b3"}},{"code_sha256_prefix":"deb46be3575f1707","entry":"save_images","repo":"agonzgarc/cross-domain-disen","repo_kind":"official","path":"run_cross_domain_disen.py","file_url":"https://github.com/agonzgarc/cross-domain-disen/blob/HEAD/run_cross_domain_disen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"deb46be3575f1707"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}