Methods › Computer Vision › Convolutions › Octave Convolution
Octave Convolution
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
An Octave Convolution (OctConv) stores and process feature maps that vary spatially “slower” at a lower spatial resolution reducing both memory and computation cost. It takes in feature maps containing tensors of two frequencies one octave apart, and extracts information directly from the low-frequency maps without the need of decoding it back to the high-frequency. The motivation is that 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.
Papers archive 2025-07-28
9 shown of 9, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Frequency Perception Network for Camouflaged Object Detection 17 Aug 2023 · 2 repositories · arXiv:2308.08924
-
DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution 15 Dec 2022 · 0 repositories · arXiv:2212.07613
-
Glioblastoma Multiforme Prognosis: MRI Missing Modality Generation, Segmentation and Radiogenomic Survival Prediction 17 Mar 2021 · 1 repository · arXiv:2104.01149
-
Mining Generalized Features for Detecting AI-Manipulated Fake Faces 27 Oct 2020 · 0 repositories · arXiv:2010.14129
-
Generalized Octave Convolutions for Learned Multi-Frequency Image Compression 24 Feb 2020 · 1 repository · arXiv:2002.10032
-
Classification of LiDAR Data Combined Octave Convolution With Capsule Network 9 Jan 2020 · 0 repositories
-
Multi-scale Octave Convolutions for Robust Speech Recognition 31 Oct 2019 · 0 repositories · arXiv:1910.14443
-
Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network 28 Jun 2019 · 2 repositories · arXiv:1906.12193
-
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution 10 Apr 2019 · 28 repositories · arXiv:1904.05049Syntology ran 14 of 34 samples · 20 unverified · 8 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 29 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Decoder | 2 |
| SSIM | 2 |
| Segmentation | 2 |
| Action Classification | 1 |
| Classification | 1 |
| Computational Efficiency | 1 |
| Denoising | 1 |
| General Classification | 1 |
| Generative Adversarial Network | 1 |
| Image Classification | 1 |
| Image Compression | 1 |
| Image Denoising | 1 |
| Image Super-Resolution | 1 |
| MS-SSIM | 1 |
| Object | 1 |
| Object Detection | 1 |
| Prediction | 1 |
| Prognosis | 1 |
| Retinal Vessel Segmentation | 1 |
| Robust Speech Recognition | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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