{"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/deep-cnns-meet-global-covariance-pooling","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","arxiv_id":"1904.06836","date":"2019-04-15","proceeding":null,"authors":["Qilong Wang","Jiangtao Xie","WangMeng Zuo","Lei Zhang","Peihua Li"],"abstract":"Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potential for improving representation and generalization abilities of deep CNNs. However, integration of global covariance pooling into deep CNNs brings two challenges: (1) robust covariance estimation given deep features of high dimension and small sample size; (2) appropriate usage of geometry of covariances. To address these challenges, we propose a global Matrix Power Normalized COVariance (MPN-COV) Pooling. Our MPN-COV conforms to a robust covariance estimator, very suitable for scenario of high dimension and small sample size. It can also be regarded as Power-Euclidean metric between covariances, effectively exploiting their geometry. Furthermore, a global Gaussian embedding network is proposed to incorporate first-order statistics into MPN-COV. For fast training of MPN-COV networks, we implement an iterative matrix square root normalization, avoiding GPU unfriendly eigen-decomposition inherent in MPN-COV. Additionally, progressive 1x1 convolutions and group convolution are introduced to compress covariance representations. The proposed methods are highly modular, readily plugged into existing deep CNNs. Extensive experiments are conducted on large-scale object classification, scene categorization, fine-grained visual recognition and texture classification, showing our methods outperform the counterparts and obtain state-of-the-art performance.","url_abs":"https://arxiv.org/abs/1904.06836v2","url_pdf":"https://arxiv.org/pdf/1904.06836v2.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":"deep-cnns-meet-global-covariance-pooling","repo_url":"https://github.com/ZhangLi-CS/GCP_Optimization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-cnns-meet-global-covariance-pooling","repo_url":"https://github.com/jiangtaoxie/MPN-COV","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-cnns-meet-global-covariance-pooling","repo_url":"https://github.com/jiangtaoxie/fast-MPN-COV","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fine-grained-visual-recognition","task_name":"Fine-Grained Visual Recognition"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"scene-classification","task_name":"Scene Classification"},{"task_slug":"texture-classification","task_name":"Texture Classification"}],"methods":[{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"iSQRT-COV-Net","rank_in_archive_order":18,"of":19,"metrics":{"Top 3 Error":"14.625"},"uses_additional_data":false},{"leaderboard":"/sota/scene-classification-on-places365-standard","task":"Scene Classification","dataset":"Places365-Standard","model":"iSQRT-COV-Net (ResNet-50)","rank_in_archive_order":2,"of":2,"metrics":{"Top 1 Error":"43.68","Top 5 Error":"13.73"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.06836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06836"}},"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/jiangtaoxie/fast-MPN-COV","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiangtaoxie/MPN-COV","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZhangLi-CS/GCP_Optimization","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":"3e3d33392b6ecdd9","entry":"CovpoolLayer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3e3d33392b6ecdd9"}},{"code_sha256_prefix":"3c7b6412a1bc9cf4","entry":"SqrtmLayer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3c7b6412a1bc9cf4"}},{"code_sha256_prefix":"5cee54d3483cad8f","entry":"TriuvecLayer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5cee54d3483cad8f"}},{"code_sha256_prefix":"7ddc2f880c6efa54","entry":"mpncovresnet101","repo":"jiangtaoxie/fast-MPN-COV","repo_kind":"official","path":"src/network/mpncovresnet.py","file_url":"https://github.com/jiangtaoxie/fast-MPN-COV/blob/HEAD/src/network/mpncovresnet.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":"7ddc2f880c6efa54"}},{"code_sha256_prefix":"0f8d5172e2842cc9","entry":"mpncovresnet50","repo":"jiangtaoxie/fast-MPN-COV","repo_kind":"official","path":"src/network/mpncovresnet.py","file_url":"https://github.com/jiangtaoxie/fast-MPN-COV/blob/HEAD/src/network/mpncovresnet.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":"0f8d5172e2842cc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}