{"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/structured-receptive-fields-in-cnns","title":"Structured Receptive Fields in CNNs","arxiv_id":"1605.02971","date":"2016-05-10","proceeding":"CVPR 2016 6","authors":["Jörn-Henrik Jacobsen","Jan van Gemert","Zhongyu Lou","Arnold W. M. Smeulders"],"abstract":"Learning powerful feature representations with CNNs is hard when training\ndata are limited. Pre-training is one way to overcome this, but it requires\nlarge datasets sufficiently similar to the target domain. Another option is to\ndesign priors into the model, which can range from tuned hyperparameters to\nfully engineered representations like Scattering Networks. We combine these\nideas into structured receptive field networks, a model which has a fixed\nfilter basis and yet retains the flexibility of CNNs. This flexibility is\nachieved by expressing receptive fields in CNNs as a weighted sum over a fixed\nbasis which is similar in spirit to Scattering Networks. The key difference is\nthat we learn arbitrary effective filter sets from the basis rather than\nmodeling the filters. This approach explicitly connects classical multiscale\nimage analysis with general CNNs. With structured receptive field networks, we\nimprove considerably over unstructured CNNs for small and medium dataset\nscenarios as well as over Scattering for large datasets. We validate our\nfindings on ILSVRC2012, Cifar-10, Cifar-100 and MNIST. As a realistic small\ndataset example, we show state-of-the-art classification results on popular 3D\nMRI brain-disease datasets where pre-training is difficult due to a lack of\nlarge public datasets in a similar domain.","url_abs":"http://arxiv.org/abs/1605.02971v2","url_pdf":"http://arxiv.org/pdf/1605.02971v2.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":"structured-receptive-fields-in-cnns","repo_url":"https://github.com/jhjacobsen/RFNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"structured-receptive-fields-in-cnns","repo_url":"https://github.com/kazemSafari/convrf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"structured-receptive-fields-in-cnns","repo_url":"https://github.com/nkarantzas/quick_draw","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.02971"}},"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/kazemSafari/convrf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nkarantzas/quick_draw","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhjacobsen/RFNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":11},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1},"listed":{"samples":7,"ran":3,"repositories":2}},"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":"d9def42110729a85","entry":"conv1x1","repo":"nkarantzas/quick_draw","repo_kind":"listed","path":"quickdraw/code/resnet_one.py","file_url":"https://github.com/nkarantzas/quick_draw/blob/HEAD/quickdraw/code/resnet_one.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"nkarantzas/quick_draw","repo_kind":"listed","path":"quickdraw/code/resnet_one.py","file_url":"https://github.com/nkarantzas/quick_draw/blob/HEAD/quickdraw/code/resnet_one.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"add437ed8ace7c35","entry":"kaiming_uniform_mod","repo":"kazemSafari/convrf","repo_kind":"listed","path":"convrf/convrf.py","file_url":"https://github.com/kazemSafari/convrf/blob/HEAD/convrf/convrf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"add437ed8ace7c35"}},{"code_sha256_prefix":"61cfa43a945cbe3b","entry":"array_to_blobproto","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"caffe-rfnn/python/caffe/io.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/caffe-rfnn/python/caffe/io.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":"61cfa43a945cbe3b"}},{"code_sha256_prefix":"5810172a0b523a23","entry":"arraylist_to_blobprotovecor_str","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"caffe-rfnn/python/caffe/io.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/caffe-rfnn/python/caffe/io.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":"5810172a0b523a23"}},{"code_sha256_prefix":"093b959c347fd2f5","entry":"blobproto_to_array","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"caffe-rfnn/python/caffe/io.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/caffe-rfnn/python/caffe/io.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":"093b959c347fd2f5"}},{"code_sha256_prefix":"a847938e3819a686","entry":"choose_color_by_layertype","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"caffe-rfnn/python/caffe/draw.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/caffe-rfnn/python/caffe/draw.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":"a847938e3819a686"}},{"code_sha256_prefix":"c5d074fc472ecffa","entry":"class_encoding","repo":"nkarantzas/quick_draw","repo_kind":"listed","path":"quickdraw/code/load_tensor_data.py","file_url":"https://github.com/nkarantzas/quick_draw/blob/HEAD/quickdraw/code/load_tensor_data.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":"c5d074fc472ecffa"}},{"code_sha256_prefix":"ca791e27612c025a","entry":"get_batch_top3score","repo":"nkarantzas/quick_draw","repo_kind":"listed","path":"quickdraw/code/scoring_functions.py","file_url":"https://github.com/nkarantzas/quick_draw/blob/HEAD/quickdraw/code/scoring_functions.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":"ca791e27612c025a"}},{"code_sha256_prefix":"2876e38623f7acbc","entry":"get_edge_label","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"caffe-rfnn/python/caffe/draw.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/caffe-rfnn/python/caffe/draw.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":"2876e38623f7acbc"}},{"code_sha256_prefix":"e0c1940893a8d18e","entry":"mnist","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"theano-rfnn/mnist_loader.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/theano-rfnn/mnist_loader.py","link_basis":"first_harvest_node","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":"e0c1940893a8d18e"}},{"code_sha256_prefix":"b51dff9353a0c6e8","entry":"one_hot","repo":"jhjacobsen/RFNN","repo_kind":"official","path":"theano-rfnn/mnist_loader.py","file_url":"https://github.com/jhjacobsen/RFNN/blob/HEAD/theano-rfnn/mnist_loader.py","link_basis":"first_harvest_node","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":"b51dff9353a0c6e8"}},{"code_sha256_prefix":"dbcec1f72e41cc02","entry":"train_function","repo":"nkarantzas/quick_draw","repo_kind":"listed","path":"quickdraw/code/training_functions.py","file_url":"https://github.com/nkarantzas/quick_draw/blob/HEAD/quickdraw/code/training_functions.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":"dbcec1f72e41cc02"}},{"code_sha256_prefix":"3090c2466499fadb","entry":"validation_summary","repo":"nkarantzas/quick_draw","repo_kind":"listed","path":"quickdraw/code/training_functions.py","file_url":"https://github.com/nkarantzas/quick_draw/blob/HEAD/quickdraw/code/training_functions.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":"3090c2466499fadb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}