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
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.
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.
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.
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.
4134b8420b4c48b5 · report
08458eb1eaf76e36 · report
123e785ddb5335b8 · report
e5535c2973c06adf · report
a0857154e91e28f9 · report
2f7853ff01cbbc29 · report
0ae841d977200ffa · report
f4c0610b55fcb289 · report
e08d9496019166da · report
739a2595c710af6b · report
4a8c216d40baf37b · report
2960ed915c2fe837 · report
fb0e7024c16a4e85 · report
bceb811dd9e9945c · report
14a2c31b31f88653 · report
e241a3df023ced79 · report
44c563b1e8c05156 · report
9b878790d728c6b8 · report
7e7c76ac270493de · report
a39394c9a8e29425 · report
d8a2457d32979202 · report
fe50a22175e3702c · report
112117a703e03d5c · report
295549ea9af0b7a4 · report
c747d9a6671d56d9 · report
a10e0b743c2016be · report
b2719846a9cc00e2 · report
244dd0289c2757ea · report
3e3e2d00d1a3acfa · report
fe3e9e11fca7ea81 · report
b650e259d7bc482b · report
21421188135068e9 · report
89ee486ad2a5cc66 · report
f262aa35d9f2b50f · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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