Papers › Exploring Randomly Wired Neural Networks for Image Recognition

Exploring Randomly Wired Neural Networks for Image Recognition

2 Apr 2019ICCV 2019 10arXiv:1904.01569archive 2025-07-28

Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He

Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do this, we first define the concept of a stochastic network generator that encapsulates the entire network generation process. Encapsulation provides a unified view of NAS and randomly wired networks. Then, we use three classical random graph models to generate randomly wired graphs for networks. The results are surprising: several variants of these random generators yield network instances that have competitive accuracy on the ImageNet benchmark. These results suggest that new efforts focusing on designing better network generators may lead to new breakthroughs by exploring less constrained search spaces with more room for novel design.

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 31 code samples harvested from 4 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 21 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): 31 samples from 4 repositories, 10 ran (10 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

JiaminRen/RandWireNN mentioned on GitHubpytorchSyntology: not harvested report
JihaoLee/Randomly_Wired_reproducibility mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: 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
hebo1221/RandWireNN mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 3 ran (0 instrument-failed) · 6 unverified report
leaderj1001/RandWireNN mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
seungwonpark/RandWireNN mentioned on GitHubpytorchSyntology: not harvested report
swdsld/RandWire_tensorflow mentioned on GitHubtfMITSyntology: 13 samples, 6 ran (0 instrument-failed) · 7 unverified report
timctho/random-wired-nn-tensorflow mentioned on GitHubtfApache-2.0Syntology: 8 samples, 1 ran (0 instrument-failed) · 7 unverified report
wolszhang/randWireNN mentioned on GitHubSyntology: 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

31 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 21 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.

10ran
21unverified

Licence: 1 of the 31 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 4 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.

hebo1221/RandWireNN community (archive-listed) 9 samples, 3 ran (0 instrument-failed) · 6 unverified
build_graph in 20 papers utils/graph.py ran Apache-2.0 (permissive) · 7a664040a2491c18 · report fixture: signature Nodes:int/0/int, cfg:Config/0/? · returned Graph · level recorded 2026-09-24
merge_configs in 11 papers utils/config_helpers.py ran fingerprinted Apache-2.0 (permissive) · 9c0c354019b5b11c · report fixture: signature config_list:list/1/dict · returned EasyDict · level recorded 2026-09-24
parse_devkit in 5 papers utils/dataloader.py ran Apache-2.0 (permissive) · 10d196b211843339 · report fixture: signature root:str/0/str · returned tuple · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
RandWireNN_train.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 913d82af53065418 · report
get_graph_info utils/graph.py unverified Apache-2.0 (permissive) · ac311b2099cb6644 · report
load_graph in 36 papers utils/graph.py unverified Apache-2.0 (permissive) · 174138ce951dc5a6 · report
train_data_loader utils/dataloader.py unverified Apache-2.0 (permissive) · 518c0532c14f0053 · report
val_data_loader utils/dataloader.py unverified Apache-2.0 (permissive) · bdbd7768b2fdb8c1 · report
validate in 313 papers RandWireNN_train.py unverified Apache-2.0 (permissive) · 2ff692a2018660a1 · report
leaderj1001/RandWireNN community (archive-listed) 1 sample, 0 ran · 1 unverified
load_data in 700 papers DropPath_RandWireNN/preprocess.py unverified MIT (permissive) · 66d8b14bac327fa0 · report
swdsld/RandWire_tensorflow community (archive-listed) 13 samples, 6 ran (0 instrument-failed) · 7 unverified
bytes_feature in 12 papers dataset/dataset_generator.py ran MIT (permissive) · d682a9593710857e · report fixture: signature value:bytes/0/? · returned Feature · level recorded 2026-09-25
flip in 32 papers
census: 3 implementations from 5 papers, 2 distinct outputs on one shared input
dataset/iter_utils.py ran MIT (permissive) · 110b12d7b7a7feff · report fixture: signature image:EagerTensor/3/int, label:int/0/int · returned tuple · level recorded 2026-09-24
int64_feature in 12 papers dataset/dataset_generator.py ran MIT (permissive) · 328d17201d9a0e68 · report fixture: signature value:int/0/int · returned Feature · level recorded 2026-09-25
int64_list_feature in 6 papers dataset/dataset_generator.py ran MIT (permissive) · f6d735872f4495ed · report fixture: returned Feature · level recorded 2026-09-25
read_meta in 7 papers dataset/cifar10/cifar10.py ran MIT (permissive) · 24c0c54d387a898f · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-24
standardization in 8 papers dataset/iter_utils.py ran MIT (permissive) · 63508099a4ccf94d · report fixture: signature image:EagerTensor/3/float, label:EagerTensor/0/int · returned tuple · level recorded 2026-09-24
build_stage network/RandWire.py unverified MIT (permissive) · efe4fed6b02397da · report
conv_block in 95 papers network/RandWire.py unverified MIT (permissive) · 925c72f289b0471c · report
graph_generator utils/graph_generator.py unverified MIT (permissive) · 03fdad149064c68e · report
pad_and_crop dataset/iter_utils.py unverified MIT (permissive) · 98f8da7ba43d02d6 · report
read_cifar10 in 5 papers dataset/cifar10/cifar10.py unverified MIT (permissive) · 133311a54c75881c · report
read_image in 73 papers dataset/mnist/mnist.py unverified MIT (permissive) · 591b652aaf3077eb · report
read_label in 13 papers dataset/mnist/mnist.py unverified MIT (permissive) · 38bfe991e2a72c25 · report
timctho/random-wired-nn-tensorflow community (archive-listed) 8 samples, 1 ran (0 instrument-failed) · 7 unverified
get_filenames in 7 papers src/dataset/imagenet.py ran Apache-2.0 (permissive) · 0b9d9456df95e57d · report fixture: signature is_training:bool/0/bool, data_dir:str/0/str · returned list · level recorded 2026-09-24
convert_to_tf_records src/dataset/imagenet_to_tfrecord.py unverified Apache-2.0 (permissive) · eebc9108bb04b0a0 · report
dataset in 10 papers src/dataset/mnist.py unverified Apache-2.0 (permissive) · 11ec2c233298a0d4 · report
download in 53 papers src/dataset/mnist.py unverified Apache-2.0 (permissive) · 0d65e022d1e2371e · report
download_dataset in 10 papers src/dataset/imagenet_to_tfrecord.py unverified Apache-2.0 (permissive) · 46b5f4c4a7bdc5c9 · report
get_total_loss src/model/util.py unverified Apache-2.0 (permissive) · 8eb610c6ecbc7249 · report
read32 src/dataset/mnist.py unverified Apache-2.0 (permissive) · aec170f547afa0ca · report

Tasks

Image ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet RandWire-WS GFLOPs 7.9 #720 of 1060 Archive leaderboard report
Image Classification ImageNet RandWire-WS Number of params 61.5M #720 of 1060 Archive leaderboard report
Image Classification ImageNet RandWire-WS Top 1 Accuracy 80.1% #720 of 1060 Archive leaderboard report
Image Classification ImageNet RandWire-WS (small) GFLOPs 0.583 #970 of 1060 Archive leaderboard report
Image Classification ImageNet RandWire-WS (small) Number of params 5.6M #970 of 1060 Archive leaderboard report
Image Classification ImageNet RandWire-WS (small) Top 1 Accuracy 74.7% #970 of 1060 Archive leaderboard report
Neural Architecture Search ImageNet RandWire-WS (small) FLOPs 583M #118 of 135 Archive leaderboard report
Neural Architecture Search ImageNet RandWire-WS (small) Params 5.6M #118 of 135 Archive leaderboard report
Neural Architecture Search ImageNet RandWire-WS (small) Top-1 Error Rate 25.3 #118 of 135 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionCosine AnnealingDense ConnectionsGlobal Average PoolingLabel SmoothingRandWireRandom Horizontal FlipRandom Resized CropReLUSGD with MomentumSoftmaxWeight Decay

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