{"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/rethinking-bottleneck-structure-for-efficient","title":"Rethinking Bottleneck Structure for Efficient Mobile Network Design","arxiv_id":"2007.02269","date":"2020-07-05","proceeding":"ECCV 2020 8","authors":["Zhou Daquan","Qibin Hou","Yunpeng Chen","Jiashi Feng","Shuicheng Yan"],"abstract":"The inverted residual block is dominating architecture design for mobile networks recently. It changes the classic residual bottleneck by introducing two design rules: learning inverted residuals and using linear bottlenecks. In this paper, we rethink the necessity of such design changes and find it may bring risks of information loss and gradient confusion. We thus propose to flip the structure and present a novel bottleneck design, called the sandglass block, that performs identity mapping and spatial transformation at higher dimensions and thus alleviates information loss and gradient confusion effectively. Extensive experiments demonstrate that, different from the common belief, such bottleneck structure is more beneficial than the inverted ones for mobile networks. In ImageNet classification, by simply replacing the inverted residual block with our sandglass block without increasing parameters and computation, the classification accuracy can be improved by more than 1.7% over MobileNetV2. On Pascal VOC 2007 test set, we observe that there is also 0.9% mAP improvement in object detection. We further verify the effectiveness of the sandglass block by adding it into the search space of neural architecture search method DARTS. With 25% parameter reduction, the classification accuracy is improved by 0.13% over previous DARTS models. Code can be found at: https://github.com/zhoudaquan/rethinking_bottleneck_design.","url_abs":"https://arxiv.org/abs/2007.02269v4","url_pdf":"https://arxiv.org/pdf/2007.02269v4.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":"rethinking-bottleneck-structure-for-efficient","repo_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"rethinking-bottleneck-structure-for-efficient","repo_url":"https://github.com/zhoudaquan/rethinking_bottleneck_design","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"rethinking-bottleneck-structure-for-efficient","repo_url":"https://github.com/Andrew-Qibin/CoordAttention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"rethinking-bottleneck-structure-for-efficient","repo_url":"https://github.com/carolchenyx/MobilenetXT-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"darts","method_name":"DARTS"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"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=2007.02269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02269"}},"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/Andrew-Qibin/ssdlite-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Andrew-Qibin/CoordAttention","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/carolchenyx/MobilenetXT-tensorflow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhoudaquan/rethinking_bottleneck_design","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"repositories":2}},"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":"a0131fb70c267a9e","entry":"conv_1x1_bn","repo":"zhoudaquan/rethinking_bottleneck_design","repo_kind":"official","path":"mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py","file_url":"https://github.com/zhoudaquan/rethinking_bottleneck_design/blob/HEAD/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a0131fb70c267a9e"}},{"code_sha256_prefix":"408e747e0425a594","entry":"conv_3x3_bn","repo":"zhoudaquan/rethinking_bottleneck_design","repo_kind":"official","path":"mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py","file_url":"https://github.com/zhoudaquan/rethinking_bottleneck_design/blob/HEAD/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"408e747e0425a594"}},{"code_sha256_prefix":"8334eff690ba0f90","entry":"group_conv_1x1_bn","repo":"zhoudaquan/rethinking_bottleneck_design","repo_kind":"official","path":"mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py","file_url":"https://github.com/zhoudaquan/rethinking_bottleneck_design/blob/HEAD/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8334eff690ba0f90"}},{"code_sha256_prefix":"4033f0f966d86b4c","entry":"add_extras","repo":"Andrew-Qibin/ssdlite-pytorch","repo_kind":"official","path":"ssd/modeling/backbone/vgg.py","file_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch/blob/HEAD/ssd/modeling/backbone/vgg.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":"4033f0f966d86b4c"}},{"code_sha256_prefix":"b3ab5e255848ed6e","entry":"add_vgg","repo":"Andrew-Qibin/ssdlite-pytorch","repo_kind":"official","path":"ssd/modeling/backbone/vgg.py","file_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch/blob/HEAD/ssd/modeling/backbone/vgg.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":"b3ab5e255848ed6e"}},{"code_sha256_prefix":"75cc7cb3f9efa8d2","entry":"compute_on_dataset","repo":"Andrew-Qibin/ssdlite-pytorch","repo_kind":"official","path":"ssd/engine/inference.py","file_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch/blob/HEAD/ssd/engine/inference.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":"75cc7cb3f9efa8d2"}},{"code_sha256_prefix":"778b1206838f15e8","entry":"conv_1x1_bn","repo":"Andrew-Qibin/ssdlite-pytorch","repo_kind":"official","path":"ssd/modeling/backbone/mobilenext.py","file_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch/blob/HEAD/ssd/modeling/backbone/mobilenext.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":"778b1206838f15e8"}},{"code_sha256_prefix":"141234d4962cebd2","entry":"conv_3x3_bn","repo":"Andrew-Qibin/ssdlite-pytorch","repo_kind":"official","path":"ssd/modeling/backbone/mobilenext.py","file_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch/blob/HEAD/ssd/modeling/backbone/mobilenext.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":"141234d4962cebd2"}},{"code_sha256_prefix":"e8df26eea356566d","entry":"sg_block_extra","repo":"Andrew-Qibin/ssdlite-pytorch","repo_kind":"official","path":"ssd/modeling/backbone/mobilenext.py","file_url":"https://github.com/Andrew-Qibin/ssdlite-pytorch/blob/HEAD/ssd/modeling/backbone/mobilenext.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":"e8df26eea356566d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}