{"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/semantic-aware-grad-gan-for-virtual-to-real","title":"Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption","arxiv_id":"1801.01726","date":"2018-01-05","proceeding":null,"authors":["Peilun Li","Xiaodan Liang","Daoyuan Jia","Eric P. Xing"],"abstract":"Recent advances in vision tasks (e.g., segmentation) highly depend on the\navailability of large-scale real-world image annotations obtained by cumbersome\nhuman labors. Moreover, the perception performance often drops significantly\nfor new scenarios, due to the poor generalization capability of models trained\non limited and biased annotations. In this work, we resort to transfer\nknowledge from automatically rendered scene annotations in virtual-world to\nfacilitate real-world visual tasks. Although virtual-world annotations can be\nideally diverse and unlimited, the discrepant data distributions between\nvirtual and real-world make it challenging for knowledge transferring. We thus\npropose a novel Semantic-aware Grad-GAN (SG-GAN) to perform virtual-to-real\ndomain adaption with the ability of retaining vital semantic information.\nBeyond the simple holistic color/texture transformation achieved by prior\nworks, SG-GAN successfully personalizes the appearance adaption for each\nsemantic region in order to preserve their key characteristic for better\nrecognition. It presents two main contributions to traditional GANs: 1) a soft\ngradient-sensitive objective for keeping semantic boundaries; 2) a\nsemantic-aware discriminator for validating the fidelity of personalized\nadaptions with respect to each semantic region. Qualitative and quantitative\nexperiments demonstrate the superiority of our SG-GAN in scene adaption over\nstate-of-the-art GANs. Further evaluations on semantic segmentation on\nCityscapes show using adapted virtual images by SG-GAN dramatically improves\nsegmentation performance than original virtual data. We release our code at\nhttps://github.com/Peilun-Li/SG-GAN.","url_abs":"http://arxiv.org/abs/1801.01726v2","url_pdf":"http://arxiv.org/pdf/1801.01726v2.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":"semantic-aware-grad-gan-for-virtual-to-real","repo_url":"https://github.com/Peilun-Li/SG-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.01726","atlas_url":"https://app.syntology.ai/?focus=1801.01726","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":"1801.01726"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.01726\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.01726"},"call":"get_concepts_for_paper(arxiv_id=\"1801.01726\")"}],"by_repo":[{"repo":"Peilun-Li/SG-GAN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"61a9fe342b9ed9ed65985088fb59a9e413a723488fe33c7fa726331ca8ac9c13","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}