Papers › Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with...

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

10 Apr 2019ICCV 2019 10arXiv:1904.05049archive 2025-07-28

Yunpeng Chen, Haoqi Fan, Bing Xu, Zhicheng Yan, Yannis Kalantidis, Marcus Rohrbach, Shuicheng Yan, Jiashi Feng

In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures. Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies. In this work, we propose to factorize the mixed feature maps by their frequencies, and design a novel Octave Convolution (OctConv) operation to store and process feature maps that vary spatially "slower" at a lower spatial resolution reducing both memory and computation cost. Unlike existing multi-scale methods, OctConv is formulated as a single, generic, plug-and-play convolutional unit that can be used as a direct replacement of (vanilla) convolutions without any adjustments in the network architecture. It is also orthogonal and complementary to methods that suggest better topologies or reduce channel-wise redundancy like group or depth-wise convolutions. We experimentally show that by simply replacing convolutions with OctConv, we can consistently boost accuracy for both image and video recognition tasks, while reducing memory and computational cost. An OctConv-equipped ResNet-152 can achieve 82.9% top-1 classification accuracy on ImageNet with merely 22.2 GFLOPs.

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

The archive's official repository (facebookresearch/OctConv) was not harvested; the 34 samples below come from 11 community repositories.

Syntology 34 code samples harvested from 11 repositories linked to this paper: 24 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 12 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): 34 samples from 11 repositories, 24 ran (11 with no instrument failure; 13 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 3 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.

28 repositories listed; official and paper-mentioned ones first.

facebookresearch/OctConv officialmentioned in papermentioned on GitHubmxnetMITSyntology: not harvested report
AnjieZheng/OctaveConv-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
SharadGitHub/OctaveUnet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
Silver-L/OctConv mentioned on GitHubtfSyntology: not harvested report
amohant4/OctConv mentioned on GitHubpytorchSyntology: not harvested report
braincreators/octconv mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
d-li14/octconv.pytorch mentioned on GitHubpytorchSyntology: 5 samples, 1 ran (1 instrument-failed) · 4 unverified report
ddddwee1/Octave-Convolution mentioned on GitHubtfSyntology: not harvested report
deeplearningforfun/OctConv mentioned on GitHubmxnetMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
gan3sh500/octaveconv-pytorch mentioned on GitHubpytorchSyntology: not harvested report
iacolippo/octconv-pytorch mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
kk1694/octaveconv-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
koshian2/OctConv-TFKeras mentioned on GitHubtfMITSyntology: not harvested report
l5shi/OCTAVE-CONVOLUTION mentioned on GitHubtfSyntology: not harvested report
lamia482/octconv-pytorch mentioned on GitHubpytorchSyntology: not harvested report
lxtGH/OctaveConv_pytorch mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (4 instrument-failed) · 1 unverified report
markliou/OctConv mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
matsuren/OctaveConv.pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
terrychenism/OctaveConv mentioned on GitHubmxnetSyntology: not harvested report
tuanzhangCS/octconv_resnet mentioned on GitHubtfSyntology: not harvested report
vivym/OctaveConv.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
xu3kev/octconv-chainer mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
zrl4836/tensorflow_octConv mentioned on GitHubtfSyntology: 3 samples, 0 ran · 3 unverified report
Manuscrit/OctaveConv_PlugAndPlay pytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
MindCode-4/code-11 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Entropy Law: The Story Behind Data Compression and LLM Performance (arXiv:2407.06645; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-6 mindsporeSyntology: not harvested report
renmada/OctConv-paddle paddleMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 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

34 samples harvested: 24 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 13 where Syntology's instrument failed) · 10 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 · honoured contract
12ran · our draft was wrong
1ran; the contract check could not run
10ran
10unverified

Licence: 9 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 11 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.

braincreators/octconv community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
benchmarks/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · 4134b8420b4c48b5 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-22
setup_logger in 122 papers benchmarks/utils.py ran MIT (permissive) · 89ee486ad2a5cc66 · report fixture: signature name:str/0/str, save_dir:str/0/str, distributed_rank:int/0/int, filename:str/0/str · returned Logger · level recorded 2026-09-25
d-li14/octconv.pytorch community (archive-listed) 5 samples, 1 ran (1 instrument-failed) · 4 unverified
conv_bn in 88 papers oct_mobilenet.py ran · our draft was wrong Apache-2.0 (permissive) · 2f7853ff01cbbc29 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
conv_dw in 13 papers oct_mobilenet.py unverified Apache-2.0 (permissive) · fe50a22175e3702c · report
oct_resnet101 oct_resnet.py unverified Apache-2.0 (permissive) · 3e3e2d00d1a3acfa · report
oct_resnet26 oct_resnet.py unverified Apache-2.0 (permissive) · fe3e9e11fca7ea81 · report
oct_resnet50 oct_resnet.py unverified Apache-2.0 (permissive) · b650e259d7bc482b · report
deeplearningforfun/OctConv community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
check_status octconv_basic/frequency_separated_layer.py ran MIT (permissive) · d8a2457d32979202 · report fixture: signature alpha_in:float/0/float, alpha_out:float/0/float · returned tuple · level recorded 2026-09-24
kk1694/octaveconv-pytorch community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
noop in 15 papers octxresnet.py ran · honoured contract fingerprinted no licence file found · pointer only · e08d9496019166da · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
tuplify octconv.py ran · our draft was wrong no licence file found · pointer only · fb0e7024c16a4e85 · report fixture: signature layer:callable/0/? · returned type · level recorded 2026-09-22
tuplify_bn octconv.py ran · our draft was wrong no licence file found · pointer only · bceb811dd9e9945c · report fixture: signature layer:callable/0/?, alpha:float/0/float · returned type · level recorded 2026-09-22
lxtGH/OctaveConv_pytorch community (archive-listed) 5 samples, 4 ran (4 instrument-failed) · 1 unverified
conv1x1 in 691 papers libs/nn/OCtaveResnet.py ran · our draft was wrong MIT (permissive) · 08458eb1eaf76e36 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers libs/nn/OCtaveResnet.py ran · our draft was wrong MIT (permissive) · e5535c2973c06adf · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int · returned Conv2d · level recorded 2026-09-22
fast_collate in 11 papers main_imagenet.py ran · our draft was wrong MIT (permissive) · 0ae841d977200ffa · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-22
flush_print main_imagenet.py ran · our draft was wrong MIT (permissive) · f4c0610b55fcb289 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-22
Octresnet50 libs/nn/OCtaveResnet.py unverified MIT (permissive) · 7e7c76ac270493de · report
markliou/OctConv community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
OctConv_block OctConv_cifar10.py ran MIT (permissive) · e241a3df023ced79 · report fixture: signature Hx:EagerTensor/4/float, Lx:EagerTensor/4/float, alpha:float/0/float, channel_no:int/0/int, kernel_size:int/0/int, activation:callable/0/? · returned tuple · level recorded 2026-09-24
OctConv_final OctConv_cifar10.py ran MIT (permissive) · 44c563b1e8c05156 · report fixture: signature Hx:EagerTensor/4/float, Lx:EagerTensor/4/float, channel_no:int/0/int, kernel_size:int/0/int, activation:callable/0/? · returned EagerTensor · level recorded 2026-09-24
OctConv_ini OctConv_cifar10.py ran MIT (permissive) · 9b878790d728c6b8 · report fixture: signature x:EagerTensor/4/float, alpha:float/0/float, channel_no:int/0/int, kernel_size:int/0/int, activation:callable/0/? · returned tuple · level recorded 2026-09-24
conv_net in 8 papers VanillaConv_cifar10.py unverified MIT (permissive) · 112117a703e03d5c · report
matsuren/OctaveConv.pytorch community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
norm_conv1x1 models/octave_resnet.py ran · our draft was wrong MIT (permissive) · 739a2595c710af6b · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, type:NoneType/0/? · returned Conv2d · level recorded 2026-09-22
norm_conv3x3 models/octave_resnet.py ran · our draft was wrong MIT (permissive) · 4a8c216d40baf37b · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, type:NoneType/0/? · returned Conv2d · level recorded 2026-09-22
oct_conv3x3 models/octave_resnet.py ran · our draft was wrong MIT (permissive) · 2960ed915c2fe837 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, type:str/0/str · returned OctConv · level recorded 2026-09-22
xu3kev/octconv-chainer community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_num_channel octconv.py ran Apache-2.0 (permissive) · c747d9a6671d56d9 · report fixture: signature channels:int/0/int, alpha:float/0/float · returned tuple · level recorded 2026-09-24
oct_add octconv.py ran fingerprinted Apache-2.0 (permissive) · b2719846a9cc00e2 · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
oct_function octconv.py ran Apache-2.0 (permissive) · 244dd0289c2757ea · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-24
zrl4836/tensorflow_octConv community (archive-listed) 3 samples, 0 ran · 3 unverified
OctConv tf_octConv.py unverified no licence file found · pointer only · 14a2c31b31f88653 · report
firstOctConv tf_octConv.py unverified no licence file found · pointer only · 295549ea9af0b7a4 · report
lastOctConv tf_octConv.py unverified no licence file found · pointer only · a10e0b743c2016be · report
Manuscrit/OctaveConv_PlugAndPlay community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
conv1x1_octave plug_and_play.py ran · our draft was wrong no licence file found · pointer only · 123e785ddb5335b8 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, alpha:float/0/float · returned OctConv2d · level recorded 2026-09-22
conv3x3_octave plug_and_play.py ran · our draft was wrong no licence file found · pointer only · a0857154e91e28f9 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int, alpha:float/0/float · returned OctConv2d · level recorded 2026-09-22
renmada/OctConv-paddle community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
rerange_index ppcls/loss/comfunc.py ran MIT (permissive) · 21421188135068e9 · report fixture: signature batch_size:int/0/int, samples_each_class:int/0/int · returned ndarray · level recorded 2026-09-24
similar_architectures paddleclas.py ran MIT (permissive) · f262aa35d9f2b50f · report fixture: signature name:str/0/str, names:list/1/str, thresh:float/0/float, topk:int/0/int · returned list · level recorded 2026-09-24
check_model_file paddleclas.py unverified MIT (permissive) · a39394c9a8e29425 · report

Tasks

Action ClassificationImage ClassificationVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 Oct-I3D + NL Acc@1 75.7 #154 of 207 Archive leaderboard report
Image Classification ImageNet Oct-ResNet-152 (SE) GFLOPs 22.2 #489 of 1060 Archive leaderboard report
Image Classification ImageNet Oct-ResNet-152 (SE) Hardware Burden 20771G #489 of 1060 Archive leaderboard report
Image Classification ImageNet Oct-ResNet-152 (SE) Number of params 66.8M #489 of 1060 Archive leaderboard report
Image Classification ImageNet Oct-ResNet-152 (SE) Operations per network pass 2.22G #489 of 1060 Archive leaderboard report
Image Classification ImageNet Oct-ResNet-152 (SE) Top 1 Accuracy 82.9% #489 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCosine AnnealingDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingGrouped ConvolutionInverted Residual BlockKaiming InitializationLabel SmoothingMax PoolingMixupOctave ConvolutionPointwise ConvolutionReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionSGDSigmoid ActivationSoftmaxSqueeze-and-Excitation Block

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