Papers › Rethinking Channel Dimensions for Efficient Model Design

Rethinking Channel Dimensions for Efficient Model Design

2 Jul 2020CVPR 2021 1arXiv:2007.00992archive 2025-07-28

Dongyoon Han, Sangdoo Yun, Byeongho Heo, Youngjoon Yoo

Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which looks like a piecewise linear function of the network stage. In this paper, we study an effective channel dimension configuration towards better performance than the convention. To this end, we empirically study how to design a single layer properly by analyzing the rank of the output feature. We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction. Based on the investigation, we propose a simple yet effective channel configuration that can be parameterized by the layer index. As a result, our proposed model following the channel parameterization achieves remarkable performance on ImageNet classification and transfer learning tasks including COCO object detection, COCO instance segmentation, and fine-grained classifications. Code and ImageNet pretrained models are available at https://github.com/clovaai/rexnet.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (clovaai/rexnet) is linked to this paper; the 8 samples below come from 3 community repositories. Syntology harvested code from clovaai/rexnet for another paper.

clovaai/rexnet: Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method.

Syntology 8 code samples harvested from 3 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 8 samples from 3 repositories, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

clovaai/rexnet officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
YeongHyeon/ReXNet-TF2 mentioned on GitHubtfMITSyntology: not harvested report
alexwitt2399/rexnet mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
lyqcom/rexnet mentioned on GitHubmindsporeSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
paperswithcode/model-index mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
ysbsb/ReXNet-PyTorch mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
2023-MindSpore-1/ms-code-34 mindsporeSyntology: not harvested report
MS-Mind/MS-Code-02 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (arXiv:2206.10589; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
mindspore-ecosystem/mindcv mindsporeSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

8 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
6ran
1unverified

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

lyqcom/rexnet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
str2bool in 533 papers config.py ran · violated contract Apache-2.0 (permissive) · 17061f7e01a6fc86 · report fixture: signature v:str/0/str · returned bool · level recorded 2026-09-22
paperswithcode/model-index community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
full_filepath modelindex/utils.py ran fingerprinted MIT (permissive) · 14cb906d9717c748 · report fixture: signature path:str/0/str, cur_filepath:str/0/str · returned str · level recorded 2026-09-24
has_at_least_one_models_key modelindex/load_model_index.py ran fingerprinted MIT (permissive) · 141717f5e0516401 · report fixture: signature lc_keys:list/1/str · returned bool · level recorded 2026-09-24
load_raw_from_markdown modelindex/utils.py ran MIT (permissive) · 2698f6291a00ce3f · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-24
lowercase_keys modelindex/utils.py ran MIT (permissive) · 26892faf1ee64a87 · report fixture: signature d:dict/0/? · returned dict · level recorded 2026-09-24
ysbsb/ReXNet-PyTorch community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py ran MIT (permissive) · f84cc119467969e4 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
load_ckpt in 31 papers utils.py ran MIT (permissive) · 0535326f88e06187 · report fixture: signature model:callable/0/?, optimizer:SGD/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-24
rand_bbox in 63 papers train_sgd_randaugv1_cutmix.py unverified MIT (permissive) here; the stored copy is pointer only · d34a085d71b8f4b5 · report

Tasks

Image ClassificationInstance SegmentationObject DetectionSemantic SegmentationTransfer Learningmodelobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ReXNet-R_3.0 Number of params 34.8M #308 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet-R_3.0 Top 1 Accuracy 84.5% #308 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet-R_2.0 Number of params 16.5M #452 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet-R_2.0 Top 1 Accuracy 83.2% #452 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_3.0 GFLOPs 3.4 #499 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_3.0 Number of params 34.7M #499 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_3.0 Top 1 Accuracy 82.8% #499 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_2.0 GFLOPs 1.5 #625 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_2.0 Number of params 19M #625 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_2.0 Top 1 Accuracy 81.6% #625 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.5 GFLOPs 0.86 #709 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.5 Number of params 9.7M #709 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.5 Top 1 Accuracy 80.3% #709 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.3 GFLOPs 0.66 #751 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.3 Number of params 7.6M #751 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.3 Top 1 Accuracy 79.5% #751 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.0 GFLOPs 0.40 #859 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.0 Number of params 4.8M #859 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_1.0 Top 1 Accuracy 77.9% #859 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_0.9 GFLOPs 0.35 #881 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_0.9 Number of params 4.1M #881 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_0.9 Top 1 Accuracy 77.2% #881 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_0.6 Number of params 2.7M #974 of 1060 Archive leaderboard report
Image Classification ImageNet ReXNet_0.6 Top 1 Accuracy 74.6% #974 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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