Papers › Rethinking Bottleneck Structure for Efficient Mobile Network Design

Rethinking Bottleneck Structure for Efficient Mobile Network Design

5 Jul 2020ECCV 2020 8arXiv:2007.02269archive 2025-07-28

Zhou Daquan, Qibin Hou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2007.02269")

Code

Syntology Ran 3 of 9 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 9 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Andrew-Qibin/ssdlite-pytorch officialmentioned in papermentioned on GitHubpytorchMIT report
zhoudaquan/rethinking_bottleneck_design officialmentioned in papermentioned on GitHubtf report
Andrew-Qibin/CoordAttention mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 3 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
6unverified

Licence: 3 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv_1x1_bn zhoudaquan/rethinking_bottleneck_design/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py official repository ran · our draft was wrong licence not identified · pointer only · a0131fb70c267a9e · report
conv_3x3_bn zhoudaquan/rethinking_bottleneck_design/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py official repository ran · our draft was wrong licence not identified · pointer only · 408e747e0425a594 · report
group_conv_1x1_bn zhoudaquan/rethinking_bottleneck_design/mobile_deployment/pytorch/InvBlock/models/imagenet/i2rnet.py official repository ran · our draft was wrong licence not identified · pointer only · 8334eff690ba0f90 · report
add_extras Andrew-Qibin/ssdlite-pytorch/ssd/modeling/backbone/vgg.py official repository unverified MIT (permissive) · 4033f0f966d86b4c · report
add_vgg Andrew-Qibin/ssdlite-pytorch/ssd/modeling/backbone/vgg.py official repository unverified MIT (permissive) · b3ab5e255848ed6e · report
compute_on_dataset Andrew-Qibin/ssdlite-pytorch/ssd/engine/inference.py official repository unverified MIT (permissive) · 75cc7cb3f9efa8d2 · report
conv_1x1_bn Andrew-Qibin/ssdlite-pytorch/ssd/modeling/backbone/mobilenext.py official repository unverified MIT (permissive) · 778b1206838f15e8 · report
conv_3x3_bn Andrew-Qibin/ssdlite-pytorch/ssd/modeling/backbone/mobilenext.py official repository unverified MIT (permissive) · 141234d4962cebd2 · report
sg_block_extra Andrew-Qibin/ssdlite-pytorch/ssd/modeling/backbone/mobilenext.py official repository unverified MIT (permissive) · e8df26eea356566d · report

Tasks

General ClassificationNeural Architecture SearchObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDARTSDepthwise ConvolutionDepthwise Separable ConvolutionInverted Residual BlockPointwise ConvolutionReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections