{"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/dual-path-networks","title":"Dual Path Networks","arxiv_id":"1707.01629","date":"2017-07-06","proceeding":"NeurIPS 2017 12","authors":["Yunpeng Chen","Jianan Li","Huaxin Xiao","Xiaojie Jin","Shuicheng Yan","Jiashi Feng"],"abstract":"In this work, we present a simple, highly efficient and modularized Dual Path\nNetwork (DPN) for image classification which presents a new topology of\nconnection paths internally. By revealing the equivalence of the\nstate-of-the-art Residual Network (ResNet) and Densely Convolutional Network\n(DenseNet) within the HORNN framework, we find that ResNet enables feature\nre-usage while DenseNet enables new features exploration which are both\nimportant for learning good representations. To enjoy the benefits from both\npath topologies, our proposed Dual Path Network shares common features while\nmaintaining the flexibility to explore new features through dual path\narchitectures. Extensive experiments on three benchmark datasets, ImagNet-1k,\nPlaces365 and PASCAL VOC, clearly demonstrate superior performance of the\nproposed DPN over state-of-the-arts. In particular, on the ImagNet-1k dataset,\na shallow DPN surpasses the best ResNeXt-101(64x4d) with 26% smaller model\nsize, 25% less computational cost and 8% lower memory consumption, and a deeper\nDPN (DPN-131) further pushes the state-of-the-art single model performance with\nabout 2 times faster training speed. Experiments on the Places365 large-scale\nscene dataset, PASCAL VOC detection dataset, and PASCAL VOC segmentation\ndataset also demonstrate its consistently better performance than DenseNet,\nResNet and the latest ResNeXt model over various applications.","url_abs":"http://arxiv.org/abs/1707.01629v2","url_pdf":"http://arxiv.org/pdf/1707.01629v2.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":"dual-path-networks","repo_url":"https://github.com/DaikiTanak/manifold_mixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/Deci-AI/super-gradients","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/alexnikop/dpn-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/bozliu/E2E-Keyword-Spotting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/crowdAI/crowdai-musical-genre-recognition-starter-kit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/cypw/DPNs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/fengjiqiang/pretrainedmodel_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/joaopauloschuler/neural-api","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"dual-path-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"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/rwightman/pytorch-dpn-pretrained","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/2023-MindSpore-1/ms-code-148","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/densenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/PaddlePaddle/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/code-implementation1/Code1/tree/main/dpn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/dpn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/dpn.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"dual-path-networks","repo_url":"https://gitlab.com/birder/birder","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":"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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dpn","method_name":"DPN"},{"method_slug":"dpn-block","method_name":"DPN Block"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"step-decay","method_name":"Step Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"dpn","name":"DPN","full_name":"Dual Path Network"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.01629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.01629"}},"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/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-148","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/densenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rwightman/pytorch-dpn-pretrained","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code1/tree/main/dpn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleClas","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/dpn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/dpn.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/crowdAI/crowdai-musical-genre-recognition-starter-kit","reach":{"status":"ok","spdx":"MIT"}},{"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://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexnikop/dpn-tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fengjiqiang/pretrainedmodel_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cypw/DPNs","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Deci-AI/super-gradients","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joaopauloschuler/neural-api","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DaikiTanak/manifold_mixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bozliu/E2E-Keyword-Spotting","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":2},"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":"d9def42110729a85","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":"d9def42110729a85"}},{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":"DaikiTanak/manifold_mixup","repo_kind":"listed","path":"dpn_mixup.py","file_url":"https://github.com/DaikiTanak/manifold_mixup/blob/HEAD/dpn_mixup.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00e569acd6b45ef0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}