{"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/pixel-difference-networks-for-efficient-edge","title":"Pixel Difference Networks for Efficient Edge Detection","arxiv_id":"2108.07009","date":"2021-08-16","proceeding":"ICCV 2021 10","authors":["Zhuo Su","Wenzhe Liu","Zitong Yu","Dewen Hu","Qing Liao","Qi Tian","Matti Pietikäinen","Li Liu"],"abstract":"Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy consuming. In addition, it is surprising that the previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. To address these issues, we propose a simple, lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue are provided to demonstrate its effectiveness, and its high training and inference efficiency. Surprisingly, when training from scratch with only the BSDS500 and VOC datasets, PiDiNet can surpass the recorded result of human perception (0.807 vs. 0.803 in ODS F-measure) on the BSDS500 dataset with 100 FPS and less than 1M parameters. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS. Results on the NYUD and Multicue datasets show similar observations. The codes are available at https://github.com/zhuoinoulu/pidinet.","url_abs":"https://arxiv.org/abs/2108.07009v1","url_pdf":"https://arxiv.org/pdf/2108.07009v1.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":"pixel-difference-networks-for-efficient-edge","repo_url":"https://github.com/zhuoinoulu/pidinet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pixel-difference-networks-for-efficient-edge","repo_url":"https://github.com/hellozhuo/pidinet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/edge-detection-on-brind","task":"Edge Detection","dataset":"BRIND","model":"PiDiNet","rank_in_archive_order":2,"of":3,"metrics":{"Number of parameters (M)":"710K","ODS":"0.789"},"uses_additional_data":false},{"leaderboard":"/sota/edge-detection-on-uded","task":"Edge Detection","dataset":"UDED","model":"PiDiNet","rank_in_archive_order":5,"of":5,"metrics":{"ODS":"0.812"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.07009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07009"}},"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/hellozhuo/pidinet","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/zhuoinoulu/pidinet","reach":null}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"c9d2f45de382359a","entry":"CDCM","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c9d2f45de382359a"}},{"code_sha256_prefix":"53821ada601de49f","entry":"CSAM","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"53821ada601de49f"}},{"code_sha256_prefix":"026700536ed63347","entry":"Conv2d","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"026700536ed63347"}},{"code_sha256_prefix":"1d50cf8c5f87cb98","entry":"MapReduce","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1d50cf8c5f87cb98"}},{"code_sha256_prefix":"94340862cd81241d","entry":"PDCBlock","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"94340862cd81241d"}},{"code_sha256_prefix":"ac153de09d9147ff","entry":"PDCBlock_converted","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ac153de09d9147ff"}},{"code_sha256_prefix":"7e54b06d4ca7e980","entry":"PiDiNet","repo":"zhuoinoulu/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/zhuoinoulu/pidinet/blob/HEAD/models/pidinet.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":"7e54b06d4ca7e980"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}