{"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/srm-a-style-based-recalibration-module-for","title":"SRM : A Style-based Recalibration Module for Convolutional Neural Networks","arxiv_id":"1903.10829","date":"2019-03-26","proceeding":null,"authors":["HyunJae Lee","Hyo-Eun Kim","Hyeonseob Nam"],"abstract":"Following the advance of style transfer with Convolutional Neural Networks\n(CNNs), the role of styles in CNNs has drawn growing attention from a broader\nperspective. In this paper, we aim to fully leverage the potential of styles to\nimprove the performance of CNNs in general vision tasks. We propose a\nStyle-based Recalibration Module (SRM), a simple yet effective architectural\nunit, which adaptively recalibrates intermediate feature maps by exploiting\ntheir styles. SRM first extracts the style information from each channel of the\nfeature maps by style pooling, then estimates per-channel recalibration weight\nvia channel-independent style integration. By incorporating the relative\nimportance of individual styles into feature maps, SRM effectively enhances the\nrepresentational ability of a CNN. The proposed module is directly fed into\nexisting CNN architectures with negligible overhead. We conduct comprehensive\nexperiments on general image recognition as well as tasks related to styles,\nwhich verify the benefit of SRM over recent approaches such as\nSqueeze-and-Excitation (SE). To explain the inherent difference between SRM and\nSE, we provide an in-depth comparison of their representational properties.","url_abs":"http://arxiv.org/abs/1903.10829v1","url_pdf":"http://arxiv.org/pdf/1903.10829v1.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":"srm-a-style-based-recalibration-module-for","repo_url":"https://github.com/EvgenyKashin/SRMnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"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":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"residual-srm","method_name":"Residual SRM"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"style-based-recalibration-module","method_name":"Style-based Recalibration Module"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"residual-srm","name":"Residual SRM","full_name":"Residual SRM"},{"slug":"style-based-recalibration-module","name":"Style-based Recalibration Module","full_name":"Style-based Recalibration Module"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"SRM-ResNet-56","rank_in_archive_order":142,"of":265,"metrics":{"Percentage correct":"95.05","Top-1 Accuracy":"95.05"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SRM-ResNet-101","rank_in_archive_order":831,"of":1060,"metrics":{"Top 1 Accuracy":"78.47%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.10829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10829"}},"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/EvgenyKashin/SRMnet","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"f5abc8215bd02a27","entry":"basic_block_factory","repo":"EvgenyKashin/SRMnet","repo_kind":"listed","path":"models/resnet_with_block.py","file_url":"https://github.com/EvgenyKashin/SRMnet/blob/HEAD/models/resnet_with_block.py","link_basis":"first_harvest_node","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":"f5abc8215bd02a27"}},{"code_sha256_prefix":"6ef392f365cc5703","entry":"conv1x1","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":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6ef392f365cc5703"}},{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","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":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}