Construct · 1 fields · 1 citations

depthwise separable convolution: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Deep learning

a factorization of a standard convolution into a per-channel spatial convolution followed by a pointwise convolution that mixes channels, cutting parameters and compute.

In deep learning, depthwise separable convolution refers to a factorization of a standard convolution into a per-channel spatial convolution followed by a pointwise convolution that mixes channels, cutting parameters and compute. This meaning comes from Chollet (2017) in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how depthwise separable convolution sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

convolution3 fields · 3 citationsjingle · one word, three constructs deep learning1 fields · 1 citationsanchor · a standalone construct learning6 fields · 14 citationsjingle · one name, six constructs

References

Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2017.195

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct