Methods › Computer Vision › Convolutions › Spatially Separable Convolution
Spatially Separable Convolution
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Spatially Separable Convolution decomposes a convolution into two separate operations. In regular convolution, if we have a 3 x 3 kernel then we directly convolve this with the image. We can divide a 3 x 3 kernel into a 3 x 1 kernel and a 1 x 3 kernel. Then, in spatially separable convolution, we first convolve the 3 x 1 kernel then the 1 x 3 kernel. This requires 6 instead of 9 parameters compared to regular convolution, and so it is more parameter efficient (additionally less matrix multiplications are required).
Image Source: Kunlun Bai
Papers archive 2025-07-28
12 shown of 12, 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.
-
SepHRNet: Generating High-Resolution Crop Maps from Remote Sensing imagery using HRNet with Separable Convolution 11 Jul 2023 · 0 repositories · arXiv:2307.05700
-
EEEA-Net: An Early Exit Evolutionary Neural Architecture Search 13 Aug 2021 · 1 repository · arXiv:2108.06156
-
Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning 22 Oct 2020 · 3 repositories · arXiv:2010.11910Syntology ran 1 of 1 samples · 0 unverified
-
RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning 14 Sep 2020 · 2 repositories · arXiv:2009.06193
-
GDP: Generalized Device Placement for Dataflow Graphs 28 Sep 2019 · 0 repositories · arXiv:1910.01578
-
Learning Data Augmentation Strategies for Object Detection 26 Jun 2019 · 6 repositories · arXiv:1906.11172Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
-
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision 29 Apr 2019 · 1 repository · arXiv:1905.03696Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
-
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection 16 Apr 2019 · 8 repositories · arXiv:1904.07392
-
ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs 27 Feb 2019 · 5 repositories · arXiv:1902.10298Syntology ran 2 of 7 samples · 5 unverified · 1 pointer-only (licence)
-
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism 16 Nov 2018 · 13 repositories · arXiv:1811.06965Syntology ran 1 of 25 samples · 24 unverified · 16 pointer-only (licence)
-
SqueezeNext: Hardware-Aware Neural Network Design 23 Mar 2018 · 8 repositories · arXiv:1803.10615Syntology ran 1 of 1 samples · 0 unverified
-
Regularized Evolution for Image Classifier Architecture Search 5 Feb 2018 · 5 repositories · arXiv:1802.01548
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.
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