{"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-pyramidal-residual-networks","title":"Deep Pyramidal Residual Networks","arxiv_id":"1610.02915","date":"2016-10-10","proceeding":"CVPR 2017 7","authors":["Dongyoon Han","Jiwhan Kim","Junmo Kim"],"abstract":"Deep convolutional neural networks (DCNNs) have shown remarkable performance\nin image classification tasks in recent years. Generally, deep neural network\narchitectures are stacks consisting of a large number of convolutional layers,\nand they perform downsampling along the spatial dimension via pooling to reduce\nmemory usage. Concurrently, the feature map dimension (i.e., the number of\nchannels) is sharply increased at downsampling locations, which is essential to\nensure effective performance because it increases the diversity of high-level\nattributes. This also applies to residual networks and is very closely related\nto their performance. In this research, instead of sharply increasing the\nfeature map dimension at units that perform downsampling, we gradually increase\nthe feature map dimension at all units to involve as many locations as\npossible. This design, which is discussed in depth together with our new\ninsights, has proven to be an effective means of improving generalization\nability. Furthermore, we propose a novel residual unit capable of further\nimproving the classification accuracy with our new network architecture.\nExperiments on benchmark CIFAR-10, CIFAR-100, and ImageNet datasets have shown\nthat our network architecture has superior generalization ability compared to\nthe original residual networks. Code is available at\nhttps://github.com/jhkim89/PyramidNet}","url_abs":"http://arxiv.org/abs/1610.02915v4","url_pdf":"http://arxiv.org/pdf/1610.02915v4.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-pyramidal-residual-networks","repo_url":"https://github.com/jhkim89/PyramidNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"deep-pyramidal-residual-networks","repo_url":"https://github.com/1490581824/PyramidNet-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-pyramidal-residual-networks","repo_url":"https://github.com/dnddnjs/pytorch-cifar10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-pyramidal-residual-networks","repo_url":"https://github.com/dyhan0920/PyramidNet-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-pyramidal-residual-networks","repo_url":"https://github.com/epfl-ml-reproducers/subspace-attack-reproduction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-pyramidal-residual-networks","repo_url":"https://github.com/marload/ConvNets-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-pyramidal-residual-networks","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"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":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"nesterov-accelerated-gradient","method_name":"Nesterov Accelerated Gradient"},{"method_slug":"pyramidnet","method_name":"PyramidNet"},{"method_slug":"pyramidal-bottleneck-residual-unit","method_name":"Pyramidal Bottleneck Residual Unit"},{"method_slug":"pyramidal-residual-unit","method_name":"Pyramidal Residual Unit"},{"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":"step-decay","method_name":"Step Decay"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"zero-padded-shortcut-connection","method_name":"Zero-padded Shortcut Connection"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pyramidal-residual-unit","name":"Pyramidal Residual Unit","full_name":"Pyramidal Residual Unit"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Deep pyramidal residual network","rank_in_archive_order":104,"of":265,"metrics":{"Percentage correct":"96.69"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.02915","atlas_url":"https://app.syntology.ai/?focus=1610.02915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02915"}},"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/epfl-ml-reproducers/subspace-attack-reproduction","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dyhan0920/PyramidNet-PyTorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dnddnjs/pytorch-cifar10","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marload/ConvNets-TensorFlow2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1490581824/PyramidNet-Keras","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhkim89/PyramidNet","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"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":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"dyhan0920/PyramidNet-PyTorch","repo_kind":"listed","path":"PyramidNet.py","file_url":"https://github.com/dyhan0920/PyramidNet-PyTorch/blob/HEAD/PyramidNet.py","link_basis":"plan_row","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":"fac5364e2f53c6db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}