{"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/lightweight-pixel-difference-networks-for","title":"Lightweight Pixel Difference Networks for Efficient Visual Representation Learning","arxiv_id":"2402.00422","date":"2024-02-01","proceeding":null,"authors":["Zhuo Su","Jiehua Zhang","Longguang Wang","Hua Zhang","Zhen Liu","Matti Pietikäinen","Li Liu"],"abstract":"Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient DNNs lies in how to balance the competing goals of achieving high accuracy and high efficiency. In this paper we propose two novel types of convolutions, dubbed \\emph{Pixel Difference Convolution (PDC) and Binary PDC (Bi-PDC)} which enjoy the following benefits: capturing higher-order local differential information, computationally efficient, and able to be integrated with existing DNNs. With PDC and Bi-PDC, we further present two lightweight deep networks named \\emph{Pixel Difference Networks (PiDiNet)} and \\emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition. Extensive experiments on popular datasets (BSDS500, ImageNet, LFW, YTF, \\emph{etc.}) show that PiDiNet and Bi-PiDiNet achieve the best accuracy-efficiency trade-off. For edge detection, PiDiNet is the first network that can be trained without ImageNet, and can achieve the human-level performance on BSDS500 at 100 FPS and with $<$1M parameters. For object recognition, among existing Binary DNNs, Bi-PiDiNet achieves the best accuracy and a nearly $2\\times$ reduction of computational cost on ResNet18. Code available at \\href{https://github.com/hellozhuo/pidinet}{https://github.com/hellozhuo/pidinet}.","url_abs":"https://arxiv.org/abs/2402.00422v1","url_pdf":"https://arxiv.org/pdf/2402.00422v1.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":"lightweight-pixel-difference-networks-for","repo_url":"https://github.com/hellozhuo/pidinet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"pdc","method_name":"PDC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.00422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00422"}},"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}],"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":"ec9e77f8e76cf69d","entry":"pidinet","repo":"hellozhuo/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/hellozhuo/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":"ec9e77f8e76cf69d"}},{"code_sha256_prefix":"d9e4c303a0445108","entry":"pidinet_small","repo":"hellozhuo/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/hellozhuo/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":"d9e4c303a0445108"}},{"code_sha256_prefix":"e2ce4e942adce73d","entry":"pidinet_tiny","repo":"hellozhuo/pidinet","repo_kind":"official","path":"models/pidinet.py","file_url":"https://github.com/hellozhuo/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":"e2ce4e942adce73d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}