{"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/defect-spectrum-a-granular-look-of-large","title":"Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics","arxiv_id":"2310.17316","date":"2023-10-26","proceeding":null,"authors":["Shuai Yang","Zhifei Chen","Pengguang Chen","Xi Fang","Yixun Liang","Shu Liu","Yingcong Chen"],"abstract":"Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models.","url_abs":"https://arxiv.org/abs/2310.17316v5","url_pdf":"https://arxiv.org/pdf/2310.17316v5.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":"defect-spectrum-a-granular-look-of-large","repo_url":"https://github.com/EnVision-Research/Defect_Spectrum","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"defect-spectrum-a-granular-look-of-large","repo_url":"https://github.com/zhangzilongc/sofs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.17316","atlas_url":"https://app.syntology.ai/?focus=2310.17316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17316"}},"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/zhangzilongc/sofs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EnVision-Research/Defect_Spectrum","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"40369adbc7a4787e","entry":"get_first_five_images","repo":"EnVision-Research/Defect_Spectrum","repo_kind":"official","path":"dataset/image_datasets.py","file_url":"https://github.com/EnVision-Research/Defect_Spectrum/blob/HEAD/dataset/image_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40369adbc7a4787e"}},{"code_sha256_prefix":"6f527bbe13c81b60","entry":"is_image_file","repo":"EnVision-Research/Defect_Spectrum","repo_kind":"official","path":"dataset/base_dataset.py","file_url":"https://github.com/EnVision-Research/Defect_Spectrum/blob/HEAD/dataset/base_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f527bbe13c81b60"}},{"code_sha256_prefix":"35db53e6de24ca77","entry":"make_dataset","repo":"EnVision-Research/Defect_Spectrum","repo_kind":"official","path":"dataset/base_dataset.py","file_url":"https://github.com/EnVision-Research/Defect_Spectrum/blob/HEAD/dataset/base_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35db53e6de24ca77"}},{"code_sha256_prefix":"17eb0a31c91b671c","entry":"normal_kl","repo":"EnVision-Research/Defect_Spectrum","repo_kind":"official","path":"models/distributions.py","file_url":"https://github.com/EnVision-Research/Defect_Spectrum/blob/HEAD/models/distributions.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17eb0a31c91b671c"}},{"code_sha256_prefix":"07591fa9422585e7","entry":"extract","repo":"EnVision-Research/Defect_Spectrum","repo_kind":"official","path":"diffusion/base_diffusion.py","file_url":"https://github.com/EnVision-Research/Defect_Spectrum/blob/HEAD/diffusion/base_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"07591fa9422585e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}