{"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/sketch-a-net-that-beats-humans","title":"Sketch-a-Net that Beats Humans","arxiv_id":"1501.07873","date":"2015-01-30","proceeding":null,"authors":["Qian Yu","Yongxin Yang","Yi-Zhe Song","Tao Xiang","Timothy Hospedales"],"abstract":"We propose a multi-scale multi-channel deep neural network framework that,\nfor the first time, yields sketch recognition performance surpassing that of\nhumans. Our superior performance is a result of explicitly embedding the unique\ncharacteristics of sketches in our model: (i) a network architecture designed\nfor sketch rather than natural photo statistics, (ii) a multi-channel\ngeneralisation that encodes sequential ordering in the sketching process, and\n(iii) a multi-scale network ensemble with joint Bayesian fusion that accounts\nfor the different levels of abstraction exhibited in free-hand sketches. We\nshow that state-of-the-art deep networks specifically engineered for photos of\nnatural objects fail to perform well on sketch recognition, regardless whether\nthey are trained using photo or sketch. Our network on the other hand not only\ndelivers the best performance on the largest human sketch dataset to date, but\nalso is small in size making efficient training possible using just CPUs.","url_abs":"http://arxiv.org/abs/1501.07873v3","url_pdf":"http://arxiv.org/pdf/1501.07873v3.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":"sketch-a-net-that-beats-humans","repo_url":"https://github.com/cmach508/sp-gra2seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"sketch-a-net-that-beats-humans","repo_url":"https://github.com/dasayan05/sketchanet-quickdraw","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sketch-a-net-that-beats-humans","repo_url":"https://github.com/sczang/dc-gra2seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sketch-recognition","task_name":"Sketch Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1501.07873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1501.07873"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/cmach508/sp-gra2seq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dasayan05/sketchanet-quickdraw","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sczang/dc-gra2seq","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"533355fb6685976b","entry":"sort_paths","repo":"sczang/dc-gra2seq","repo_kind":"listed","path":"sample.py","file_url":"https://github.com/sczang/dc-gra2seq/blob/HEAD/sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"533355fb6685976b"}},{"code_sha256_prefix":"7ef0d714fcf4f5fd","entry":"sort_paths","repo":"sczang/dc-gra2seq","repo_kind":"listed","path":"calculate-Ret.py","file_url":"https://github.com/sczang/dc-gra2seq/blob/HEAD/calculate-Ret.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7ef0d714fcf4f5fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}