{"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/on-network-design-spaces-for-visual","title":"On Network Design Spaces for Visual Recognition","arxiv_id":"1905.13214","date":"2019-05-30","proceeding":"ICCV 2019 10","authors":["Ilija Radosavovic","Justin Johnson","Saining Xie","Wan-Yen Lo","Piotr Dollár"],"abstract":"Over the past several years progress in designing better neural network architectures for visual recognition has been substantial. To help sustain this rate of progress, in this work we propose to reexamine the methodology for comparing network architectures. In particular, we introduce a new comparison paradigm of distribution estimates, in which network design spaces are compared by applying statistical techniques to populations of sampled models, while controlling for confounding factors like network complexity. Compared to current methodologies of comparing point and curve estimates of model families, distribution estimates paint a more complete picture of the entire design landscape. As a case study, we examine design spaces used in neural architecture search (NAS). We find significant statistical differences between recent NAS design space variants that have been largely overlooked. Furthermore, our analysis reveals that the design spaces for standard model families like ResNeXt can be comparable to the more complex ones used in recent NAS work. We hope these insights into distribution analysis will enable more robust progress toward discovering better networks for visual recognition.","url_abs":"https://arxiv.org/abs/1905.13214v1","url_pdf":"https://arxiv.org/pdf/1905.13214v1.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":"on-network-design-spaces-for-visual","repo_url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-network-design-spaces-for-visual","repo_url":"https://github.com/facebookresearch/nds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"on-network-design-spaces-for-visual","repo_url":"https://github.com/facebookresearch/pycls","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-network-design-spaces-for-visual","repo_url":"https://github.com/feymanpriv/pymetric","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"on-network-design-spaces-for-visual","repo_url":"https://github.com/tomomasayamasaki/RBFleX-NAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-network-design-spaces-for-visual","repo_url":"https://github.com/tuggeluk/pycls","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.13214","atlas_url":"https://app.syntology.ai/?focus=1905.13214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.13214"}},"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/tuggeluk/pycls","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/pycls","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/nds","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/feymanpriv/pymetric","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tomomasayamasaki/RBFleX-NAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"ran":7,"ran_violates":1,"unverified":4},"by_repo_kind":{"listed":{"samples":14,"ran":10,"repositories":3}},"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":10,"samples":[{"code_sha256_prefix":"3122aea73ebb5edf","entry":"ComputeVertexChannels","repo":"Edge-AI-Acceleration-Lab/RBFleX-NAS","repo_kind":"listed","path":"designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py","file_url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS/blob/HEAD/designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3122aea73ebb5edf"}},{"code_sha256_prefix":"77137d76f02e37fe","entry":"Truncate","repo":"Edge-AI-Acceleration-Lab/RBFleX-NAS","repo_kind":"listed","path":"designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py","file_url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS/blob/HEAD/designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77137d76f02e37fe"}},{"code_sha256_prefix":"f623b3e3625d4e42","entry":"cache_url","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/io.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/io.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f623b3e3625d4e42"}},{"code_sha256_prefix":"4136b6e9df422178","entry":"complexity_batchnorm2d","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/net.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/net.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"4136b6e9df422178"}},{"code_sha256_prefix":"b299737079f619a1","entry":"complexity_conv2d","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/net.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/net.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b299737079f619a1"}},{"code_sha256_prefix":"ee4b7c6aef3ebb1f","entry":"complexity_maxpool2d","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/net.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/net.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"ee4b7c6aef3ebb1f"}},{"code_sha256_prefix":"8e4e129cb77e7f8b","entry":"get_logger","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/logging.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/logging.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"8e4e129cb77e7f8b"}},{"code_sha256_prefix":"803bcd86e3301891","entry":"time_string","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/meters.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/meters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"803bcd86e3301891"}},{"code_sha256_prefix":"b997b70e1ac2c2f1","entry":"topk_errors","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/meters.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/meters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b997b70e1ac2c2f1"}},{"code_sha256_prefix":"8ba24560996e7d76","entry":"unwrap_model","repo":"tuggeluk/pycls","repo_kind":"listed","path":"pycls/core/net.py","file_url":"https://github.com/tuggeluk/pycls/blob/HEAD/pycls/core/net.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ba24560996e7d76"}},{"code_sha256_prefix":"9640a6667c162560","entry":"Projection","repo":"Edge-AI-Acceleration-Lab/RBFleX-NAS","repo_kind":"listed","path":"designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py","file_url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS/blob/HEAD/designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.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":"9640a6667c162560"}},{"code_sha256_prefix":"e10bd0e3f25f2b57","entry":"download_url","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/io.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/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":false,"mcp_get_code":{"code_sha256":"e10bd0e3f25f2b57"}},{"code_sha256_prefix":"7defe868d1a6d115","entry":"dump_log_data","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/logging.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/logging.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":false,"mcp_get_code":{"code_sha256":"7defe868d1a6d115"}},{"code_sha256_prefix":"99b17e191b358f21","entry":"float_to_decimal","repo":"feymanpriv/pymetric","repo_kind":"listed","path":"metric/core/logging.py","file_url":"https://github.com/feymanpriv/pymetric/blob/HEAD/metric/core/logging.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":false,"mcp_get_code":{"code_sha256":"99b17e191b358f21"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}