Methods › Computer Vision › Convolutional Neural Networks › SqueezeNeXt

SqueezeNeXt

3 papers tagged archive 2025-07-28

Introduced by Amir Gholami et al. in SqueezeNext: Hardware-Aware Neural Network Design

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SqueezeNeXt is a type of convolutional neural network that uses the SqueezeNet architecture as a baseline, but makes a number of changes. First, a more aggressive channel reduction is used by incorporating a two-stage squeeze module. This significantly reduces the total number of parameters used with the 3×3 convolutions. Secondly, it uses separable 3 × 3 convolutions to further reduce the model size, and removes the additional 1×1 branch after the squeeze module. Thirdly, the network use an element-wise addition skip connection similar to that of ResNet architecture.

Paper Source See Code · osmr/imgclsmob

Papers archive 2025-07-28

3 shown of 3, 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.

HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
29 Apr 2019 · 1 repository · arXiv:1905.03696

Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
27 Feb 2019 · 5 repositories · arXiv:1902.10298

Syntology ran 2 of 7 samples · 5 unverified · 1 pointer-only (licence)
SqueezeNext: Hardware-Aware Neural Network Design
23 Mar 2018 · 8 repositories · arXiv:1803.10615

Syntology ran 1 of 1 samples · 0 unverified

Tasks archive 2025-07-28

3 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
Clustering Multivariate Time Series	1
Multivariate Time Series Imputation	1
Quantization	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

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

Convolutional Neural Networks

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