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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.05049")

Code

Syntology Ran 14 of 34 code samples harvested from 11 repositories linked to this paper; 20 have no recorded run. Of those that ran: 1 ran · honoured contract; 12 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 34 samples from 11 repositories, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

facebookresearch/OctConv officialmentioned in papermentioned on GitHubmxnetMIT report
AnjieZheng/OctaveConv-Pytorch mentioned on GitHubpytorch report
SharadGitHub/OctaveUnet mentioned on GitHubpytorch report
Silver-L/OctConv mentioned on GitHubtf report
amohant4/OctConv mentioned on GitHubpytorch report
braincreators/octconv mentioned on GitHubpytorchMIT report
d-li14/octconv.pytorch mentioned on GitHubpytorch report
ddddwee1/Octave-Convolution mentioned on GitHubtf report
deeplearningforfun/OctConv mentioned on GitHubmxnetMIT report
gan3sh500/octaveconv-pytorch mentioned on GitHubpytorch report
iacolippo/octconv-pytorch mentioned on GitHubpytorchApache-2.0 report
kk1694/octaveconv-pytorch mentioned on GitHubpytorch report
koshian2/OctConv-TFKeras mentioned on GitHubtfMIT report
l5shi/OCTAVE-CONVOLUTION mentioned on GitHubtf report
lamia482/octconv-pytorch mentioned on GitHubpytorch report
lxtGH/OctaveConv_pytorch mentioned on GitHubpytorch report
markliou/OctConv mentioned on GitHubtfMIT report
matsuren/OctaveConv.pytorch mentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
terrychenism/OctaveConv mentioned on GitHubmxnet report
tuanzhangCS/octconv_resnet mentioned on GitHubtf report
vivym/OctaveConv.pytorch mentioned on GitHubpytorchMIT report
xu3kev/octconv-chainer mentioned on GitHubpytorchApache-2.0 report
zrl4836/tensorflow_octConv mentioned on GitHubtf 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

34 samples harvested; 14 ran; 1 honoured the contract we drafted; 20 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
12ran · our draft was wrong
1ran · fixture could not drive it
20unverified

Licence: 8 of the 34 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 11 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

accuracy braincreators/octconv/benchmarks/utils.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 4134b8420b4c48b5 · report
conv1x1 lxtGH/OctaveConv_pytorch/libs/nn/OCtaveResnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 08458eb1eaf76e36 · report
conv1x1_octave Manuscrit/OctaveConv_PlugAndPlay/plug_and_play.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 123e785ddb5335b8 · report
conv3x3 lxtGH/OctaveConv_pytorch/libs/nn/OCtaveResnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · e5535c2973c06adf · report
conv3x3_octave Manuscrit/OctaveConv_PlugAndPlay/plug_and_play.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · a0857154e91e28f9 · report
conv_bn d-li14/octconv.pytorch/oct_mobilenet.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 2f7853ff01cbbc29 · report
fast_collate lxtGH/OctaveConv_pytorch/main_imagenet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 0ae841d977200ffa · report
flush_print lxtGH/OctaveConv_pytorch/main_imagenet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · f4c0610b55fcb289 · report
noop kk1694/octaveconv-pytorch/octxresnet.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · e08d9496019166da · report
norm_conv1x1 matsuren/OctaveConv.pytorch/models/octave_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 739a2595c710af6b · report
norm_conv3x3 matsuren/OctaveConv.pytorch/models/octave_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 4a8c216d40baf37b · report
oct_conv3x3 matsuren/OctaveConv.pytorch/models/octave_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 2960ed915c2fe837 · report
tuplify kk1694/octaveconv-pytorch/octconv.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · fb0e7024c16a4e85 · report
tuplify_bn kk1694/octaveconv-pytorch/octconv.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · bceb811dd9e9945c · report
OctConv zrl4836/tensorflow_octConv/tf_octConv.py community (archive-listed) unverified no licence file found · pointer only · 14a2c31b31f88653 · report
OctConv_block markliou/OctConv/OctConv_cifar10.py community (archive-listed) unverified MIT (permissive) · e241a3df023ced79 · report
OctConv_final markliou/OctConv/OctConv_cifar10.py community (archive-listed) unverified MIT (permissive) · 44c563b1e8c05156 · report
OctConv_ini markliou/OctConv/OctConv_cifar10.py community (archive-listed) unverified MIT (permissive) · 9b878790d728c6b8 · report
Octresnet50 lxtGH/OctaveConv_pytorch/libs/nn/OCtaveResnet.py community (archive-listed) unverified MIT (permissive) · 7e7c76ac270493de · report
check_model_file renmada/OctConv-paddle/paddleclas.py community (archive-listed) unverified MIT (permissive) · a39394c9a8e29425 · report
check_status deeplearningforfun/OctConv/octconv_basic/frequency_separated_layer.py community (archive-listed) unverified MIT (permissive) · d8a2457d32979202 · report
conv_dw d-li14/octconv.pytorch/oct_mobilenet.py community (archive-listed) unverified Apache-2.0 (permissive) · fe50a22175e3702c · report
conv_net markliou/OctConv/VanillaConv_cifar10.py community (archive-listed) unverified MIT (permissive) · 112117a703e03d5c · report
firstOctConv zrl4836/tensorflow_octConv/tf_octConv.py community (archive-listed) unverified no licence file found · pointer only · 295549ea9af0b7a4 · report
get_num_channel xu3kev/octconv-chainer/octconv.py community (archive-listed) unverified Apache-2.0 (permissive) · c747d9a6671d56d9 · report
lastOctConv zrl4836/tensorflow_octConv/tf_octConv.py community (archive-listed) unverified no licence file found · pointer only · a10e0b743c2016be · report
oct_add xu3kev/octconv-chainer/octconv.py community (archive-listed) unverified Apache-2.0 (permissive) · b2719846a9cc00e2 · report
oct_function xu3kev/octconv-chainer/octconv.py community (archive-listed) unverified Apache-2.0 (permissive) · 244dd0289c2757ea · report
oct_resnet101 d-li14/octconv.pytorch/oct_resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · 3e3e2d00d1a3acfa · report
oct_resnet26 d-li14/octconv.pytorch/oct_resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · fe3e9e11fca7ea81 · report
oct_resnet50 d-li14/octconv.pytorch/oct_resnet.py community (archive-listed) unverified Apache-2.0 (permissive) · b650e259d7bc482b · report
rerange_index renmada/OctConv-paddle/ppcls/loss/comfunc.py community (archive-listed) unverified MIT (permissive) · 21421188135068e9 · report
setup_logger braincreators/octconv/benchmarks/utils.py community (archive-listed) unverified MIT (permissive) · 89ee486ad2a5cc66 · report
similar_architectures renmada/OctConv-paddle/paddleclas.py community (archive-listed) unverified MIT (permissive) · f262aa35d9f2b50f · 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