Papers › On Network Design Spaces for Visual Recognition

On Network Design Spaces for Visual Recognition

30 May 2019ICCV 2019 10arXiv:1905.13214archive 2025-07-28

Ilija Radosavovic, Justin Johnson, Saining Xie, Wan-Yen Lo, Piotr Dollár

Over the past several years progress in designing better neural network architectures for visual recognition has been substantial. To help sustain this rate of progress, in this work we propose to reexamine the methodology for comparing network architectures. In particular, we introduce a new comparison paradigm of distribution estimates, in which network design spaces are compared by applying statistical techniques to populations of sampled models, while controlling for confounding factors like network complexity. Compared to current methodologies of comparing point and curve estimates of model families, distribution estimates paint a more complete picture of the entire design landscape. As a case study, we examine design spaces used in neural architecture search (NAS). We find significant statistical differences between recent NAS design space variants that have been largely overlooked. Furthermore, our analysis reveals that the design spaces for standard model families like ResNeXt can be comparable to the more complex ones used in recent NAS work. We hope these insights into distribution analysis will enable more robust progress toward discovering better networks for visual recognition.

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

Syntology 14 code samples harvested from 3 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 3 repositories, 12 ran (10 with no instrument failure; 2 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.

Edge-AI-Acceleration-Lab/RBFleX-NAS mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
facebookresearch/nds mentioned on GitHubMITSyntology: not harvested report
facebookresearch/pycls mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified) and 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
feymanpriv/pymetric mentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report
tomomasayamasaki/RBFleX-NAS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search (arXiv:2001.00326; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
tuggeluk/pycls mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 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
1ran · our draft was wrong
1ran; the contract check could not run
9ran
2unverified

Licence: 10 of the 14 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 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.

Edge-AI-Acceleration-Lab/RBFleX-NAS community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
ComputeVertexChannels designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted MIT (permissive) · 3122aea73ebb5edf · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, matrix:ndarray/2/int · returned list · level recorded 2026-09-22
Truncate designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py ran · our draft was wrong fingerprinted MIT (permissive) · 77137d76f02e37fe · report fixture: signature inputs:Tensor/4/float, channels:int/0/int · returned Tensor · level recorded 2026-09-22
Projection in 10 papers designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py unverified MIT (permissive) · 9640a6667c162560 · report
feymanpriv/pymetric community (archive-listed) 10 samples, 9 ran (0 instrument-failed) · 1 unverified
cache_url metric/core/io.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · f623b3e3625d4e42 · report fixture: signature url_or_file:str/0/str, cache_dir:str/0/str · returned str · level recorded 2026-09-24
complexity_batchnorm2d metric/core/net.py ran MIT recorded; this copy not marked cleared · pointer only · 4136b6e9df422178 · report fixture: signature cx:dict/0/?, w_in:int/0/int · returned dict · level recorded 2026-09-24
complexity_conv2d metric/core/net.py ran MIT recorded; this copy not marked cleared · pointer only · b299737079f619a1 · report fixture: signature cx:dict/0/?, w_in:int/0/int, w_out:int/0/int, k:int/0/int, stride:int/0/int, padding:int/0/int, groups:int/0/int, bias:bool/0/bool · returned dict · level recorded 2026-09-24
complexity_maxpool2d metric/core/net.py ran MIT recorded; this copy not marked cleared · pointer only · ee4b7c6aef3ebb1f · report fixture: signature cx:dict/0/?, k:int/0/int, stride:int/0/int, padding:int/0/int · returned dict · level recorded 2026-09-24
dump_log_data metric/core/logging.py ran MIT recorded; this copy not marked cleared · pointer only · 7defe868d1a6d115 · report fixture: signature data:dict/0/?, data_type:str/0/str, prec:int/0/int · returned str · level recorded 2026-09-25
float_to_decimal metric/core/logging.py ran MIT recorded; this copy not marked cleared · pointer only · 99b17e191b358f21 · report fixture: signature data:dict/0/?, prec:int/0/int · returned dict · level recorded 2026-09-25
get_logger in 383 papers metric/core/logging.py ran MIT recorded; this copy not marked cleared · pointer only · 8e4e129cb77e7f8b · report fixture: signature name:str/0/str · returned Logger · level recorded 2026-09-24
time_string metric/core/meters.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 803bcd86e3301891 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-24
topk_errors metric/core/meters.py ran MIT recorded; this copy not marked cleared · pointer only · b997b70e1ac2c2f1 · report fixture: signature preds:Tensor/2/float, labels:Tensor/1/int, ks:list/1/int · returned list · level recorded 2026-09-24
download_url in 32 papers metric/core/io.py unverified MIT recorded; this copy not marked cleared · pointer only · e10bd0e3f25f2b57 · report
tuggeluk/pycls community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
unwrap_model in 41 papers pycls/core/net.py ran · violated contract MIT (permissive) · 8ba24560996e7d76 · report fixture: signature model:callable/0/? · returned SimpleModel · level recorded 2026-09-22

Tasks

Neural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationLSTMReLUResNeXtResNeXt BlockResidual ConnectionSigmoid ActivationSoftmaxTanh Activation

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