Papers › Non-deep Networks

Non-deep Networks

14 Oct 2021arXiv:2110.07641archive 2025-07-28

Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun

Depth is the hallmark of deep neural networks. But more depth means more sequential computation and higher latency. This begs the question -- is it possible to build high-performing "non-deep" neural networks? We show that it is. To do so, we use parallel subnetworks instead of stacking one layer after another. This helps effectively reduce depth while maintaining high performance. By utilizing parallel substructures, we show, for the first time, that a network with a depth of just 12 can achieve top-1 accuracy over 80% on ImageNet, 96% on CIFAR10, and 81% on CIFAR100. We also show that a network with a low-depth (12) backbone can achieve an AP of 48% on MS-COCO. We analyze the scaling rules for our design and show how to increase performance without changing the network's depth. Finally, we provide a proof of concept for how non-deep networks could be used to build low-latency recognition systems. Code is available at https://github.com/imankgoyal/NonDeepNetworks.

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 18 code samples harvested from 3 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 4 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: official repository: 12 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 6 samples from 2 repositories, 4 ran (0 with no instrument failure; 4 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.

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.

imankgoyal/NonDeepNetworks officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 12 samples, 8 ran (1 instrument-failed) · 4 unverified report
Pritam-N/ParNet mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
hexhowells/Neural-Network-Implementations pytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
mindspore-courses/External-Attention-MindSpore 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.

Code Syntology ran Syntology

18 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
5ran
6unverified

Licence: 3 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, 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.

imankgoyal/NonDeepNetworks official repository 12 samples, 8 ran (1 instrument-failed) · 4 unverified
adapt_input_conv in 8 papers
census: 2 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
imagenet/timm/models/helpers.py ran; the contract check could not run (RAISES) BSD-3-Clause (permissive) · c58578dcfe39d5e3 · report fixture: signature in_chans:int/0/int, conv_weight:Tensor/4/float · returned Tensor · level recorded 2026-09-22
downsample_avg in 9 papers imagenet/timm/models/resnet.py ran BSD-3-Clause (permissive) · d0be08be473e0f71 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, first_dilation:NoneType/0/?, norm_layer:callable/0/? · returned Sequential · level recorded 2026-09-24
downsample_conv in 14 papers imagenet/timm/models/resnet.py ran BSD-3-Clause (permissive) · eea0376ea397a1c7 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, first_dilation:NoneType/0/?, norm_layer:callable/0/? · returned Sequential · level recorded 2026-09-24
get_padding in 84 papers imagenet/timm/models/resnet.py ran · honoured contract fingerprinted BSD-3-Clause (permissive) here; the stored copy is pointer only · 9b02c1068795fd5b · report fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
is_model in 24 papers imagenet/timm/models/registry.py ran · violated contract BSD-3-Clause (permissive) here; the stored copy is pointer only · cd2a47ded9dd84cf · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-25
list_models in 16 papers imagenet/timm/models/registry.py ran BSD-3-Clause (permissive) · a7d77cefce03249c · report fixture: signature filter:str/0/str, module:str/0/str, pretrained:bool/0/bool, exclude_filters:str/0/str · returned list · level recorded 2026-09-24
load_state_dict in 114 papers imagenet/timm/models/helpers.py ran BSD-3-Clause (permissive) · bc3a13e8155e8140 · report fixture: signature checkpoint_path:str/0/str, use_ema:bool/0/bool · returned OrderedDict · level recorded 2026-09-25
register_model in 68 papers imagenet/timm/models/registry.py ran BSD-3-Clause (permissive) · 99e9e0964c9cad5a · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
broadcast_receive imagenet/timm/models/simplenet.py unverified BSD-3-Clause (permissive) · c2dbae15a7438840 · report
create_model in 163 papers imagenet/timm/models/factory.py unverified BSD-3-Clause (permissive) · 8819f9c15124c943 · report
receive imagenet/timm/models/simplenet.py unverified BSD-3-Clause (permissive) · b6b952edfef8899a · report
resume_checkpoint in 13 papers imagenet/timm/models/helpers.py unverified BSD-3-Clause (permissive) here; the stored copy is pointer only · 102b75f3481035d1 · report
Pritam-N/ParNet community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
activation_func parnet.py ran · our draft was wrong MIT (permissive) · 22d0e0cf940313f8 · report fixture: signature activation:str/0/str · returned ReLU · level recorded 2026-09-22
conv_sampler parnet.py ran · our draft was wrong MIT (permissive) · a2c29db895f66535 · report fixture: signature kernel_size:int/0/int, stride:int/0/int, groups:int/0/int · returned partial · level recorded 2026-09-22
conv_bn in 88 papers parnet.py unverified MIT (permissive) · ce72bd6274c553ef · report
hexhowells/Neural-Network-Implementations community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
ParNetSmall models/ParNet/parnet.py ran · our draft was wrong MIT (permissive) · 700f05640a36068a · report fixture: signature in_channels:int/0/int, num_classes:int/0/int · returned ParNet · level recorded 2026-09-22
conv_bn in 88 papers models/ParNet/parnet.py ran · our draft was wrong MIT (permissive) · c8af9941c8954a90 · report fixture: signature in_c:int/0/int, out_c:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, groups:int/0/int · returned Sequential · level recorded 2026-09-22
scale_dim models/ParNet/parnet.py unverified MIT (permissive) · b39c1c629a22b4fe · report

Tasks

Image ClassificationObject DetectionReal-Time Object Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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