{"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/pcanet-a-simple-deep-learning-baseline-for","title":"PCANet: A Simple Deep Learning Baseline for Image Classification?","arxiv_id":"1404.3606","date":"2014-04-14","proceeding":null,"authors":["Tsung-Han Chan","Kui Jia","Shenghua Gao","Jiwen Lu","Zinan Zeng","Yi Ma"],"abstract":"In this work, we propose a very simple deep learning network for image\nclassification which comprises only the very basic data processing components:\ncascaded principal component analysis (PCA), binary hashing, and block-wise\nhistograms. In the proposed architecture, PCA is employed to learn multistage\nfilter banks. It is followed by simple binary hashing and block histograms for\nindexing and pooling. This architecture is thus named as a PCA network (PCANet)\nand can be designed and learned extremely easily and efficiently. For\ncomparison and better understanding, we also introduce and study two simple\nvariations to the PCANet, namely the RandNet and LDANet. They share the same\ntopology of PCANet but their cascaded filters are either selected randomly or\nlearned from LDA. We have tested these basic networks extensively on many\nbenchmark visual datasets for different tasks, such as LFW for face\nverification, MultiPIE, Extended Yale B, AR, FERET datasets for face\nrecognition, as well as MNIST for hand-written digits recognition.\nSurprisingly, for all tasks, such a seemingly naive PCANet model is on par with\nthe state of the art features, either prefixed, highly hand-crafted or\ncarefully learned (by DNNs). Even more surprisingly, it sets new records for\nmany classification tasks in Extended Yale B, AR, FERET datasets, and MNIST\nvariations. Additional experiments on other public datasets also demonstrate\nthe potential of the PCANet serving as a simple but highly competitive baseline\nfor texture classification and object recognition.","url_abs":"http://arxiv.org/abs/1404.3606v2","url_pdf":"http://arxiv.org/pdf/1404.3606v2.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":"pcanet-a-simple-deep-learning-baseline-for","repo_url":"https://github.com/Ldpe2G/PCANet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"pcanet-a-simple-deep-learning-baseline-for","repo_url":"https://github.com/lucasleesw/PCANet_python_ver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"texture-classification","task_name":"Texture Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"lda","method_name":"LDA"},{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"PCANet","rank_in_archive_order":253,"of":265,"metrics":{"Percentage correct":"78.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"PCANet","rank_in_archive_order":42,"of":81,"metrics":{"Percentage error":"0.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1404.3606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1404.3606"}},"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/lucasleesw/PCANet_python_ver","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ldpe2G/PCANet","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"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":0,"samples":[{"code_sha256_prefix":"af855a4f120433e9","entry":"load_CIFAR_batch","repo":"lucasleesw/PCANet_python_ver","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/lucasleesw/PCANet_python_ver/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af855a4f120433e9"}},{"code_sha256_prefix":"3f56553edd2ec3aa","entry":"load_mnist","repo":"lucasleesw/PCANet_python_ver","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/lucasleesw/PCANet_python_ver/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f56553edd2ec3aa"}},{"code_sha256_prefix":"92ee7e4e2a6fd8f1","entry":"load_mnist_2_0","repo":"lucasleesw/PCANet_python_ver","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/lucasleesw/PCANet_python_ver/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92ee7e4e2a6fd8f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}