{"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/convolutional-normalization-improving-deep","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","arxiv_id":"2103.00673","date":"2021-03-01","proceeding":"NeurIPS 2021 12","authors":["Sheng Liu","Xiao Li","Yuexiang Zhai","Chong You","Zhihui Zhu","Carlos Fernandez-Granda","Qing Qu"],"abstract":"Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve robustness. For ConvNets, most existing methods are based on penalizing or normalizing weight matrices derived from concatenating or flattening the convolutional kernels. These methods often destroy or ignore the benign convolutional structure of the kernels; therefore, they are often expensive or impractical for deep ConvNets. In contrast, we introduce a simple and efficient \"Convolutional Normalization\" (ConvNorm) method that can fully exploit the convolutional structure in the Fourier domain and serve as a simple plug-and-play module to be conveniently incorporated into any ConvNets. Our method is inspired by recent work on preconditioning methods for convolutional sparse coding and can effectively promote each layer's channel-wise isometry. Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets. Applied to classification under noise corruptions and generative adversarial network (GAN), we show that the ConvNorm improves the robustness of common ConvNets such as ResNet and the performance of GAN. We verify our findings via numerical experiments on CIFAR and ImageNet.","url_abs":"https://arxiv.org/abs/2103.00673v2","url_pdf":"https://arxiv.org/pdf/2103.00673v2.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":"convolutional-normalization-improving-deep","repo_url":"https://github.com/shengliu66/ConvNorm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"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":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.00673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00673"}},"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":"deterministic:regex_extraction","url":"https://github.com/shengliu66/ConvNorm","reach":null}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":6,"samples":[{"code_sha256_prefix":"148009db2b22f00b","entry":"ONINorm","repo":"shengliu66/ConvNorm","repo_kind":"official","path":"models/oni.py","file_url":"https://github.com/shengliu66/ConvNorm/blob/HEAD/models/oni.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"148009db2b22f00b"}},{"code_sha256_prefix":"e4c56231f537ea6d","entry":"ONINorm_colum","repo":"shengliu66/ConvNorm","repo_kind":"official","path":"models/oni.py","file_url":"https://github.com/shengliu66/ConvNorm/blob/HEAD/models/oni.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4c56231f537ea6d"}},{"code_sha256_prefix":"95248d4989691e33","entry":"ONI_Conv2d","repo":"shengliu66/ConvNorm","repo_kind":"official","path":"models/oni.py","file_url":"https://github.com/shengliu66/ConvNorm/blob/HEAD/models/oni.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95248d4989691e33"}},{"code_sha256_prefix":"2462218e08497820","entry":"compl_mul_2D","repo":"shengliu66/ConvNorm","repo_kind":"official","path":"models/prec_conv.py","file_url":"https://github.com/shengliu66/ConvNorm/blob/HEAD/models/prec_conv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2462218e08497820"}},{"code_sha256_prefix":"0e861ec43a51110b","entry":"complex_abs","repo":"shengliu66/ConvNorm","repo_kind":"official","path":"models/prec_conv.py","file_url":"https://github.com/shengliu66/ConvNorm/blob/HEAD/models/prec_conv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e861ec43a51110b"}},{"code_sha256_prefix":"4dad88c96a25c5e7","entry":"cosine_rampdown","repo":"shengliu66/ConvNorm","repo_kind":"official","path":"models/prec_conv.py","file_url":"https://github.com/shengliu66/ConvNorm/blob/HEAD/models/prec_conv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4dad88c96a25c5e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}