Methods › Computer Vision › Light-weight neural networks › SqueezeNet

SqueezeNet

97 papers tagged archive 2025-07-28

Introduced by Forrest N. Iandola et al. in SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

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

SqueezeNet is a convolutional neural network that employs design strategies to reduce the number of parameters, notably with the use of fire modules that "squeeze" parameters using 1x1 convolutions.

PaperSourceSee Code · pytorch/vision

Papers archive 2025-07-28

30 shown of 97, 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.

Tasks archive 2025-07-28

20 shown of 93 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Transfer Learning16
General Classification11
Object Detection10
object-detection10
Classification9
GPU9
Image Classification9
Data Augmentation6
image-classification6
Deep Learning5
Specificity5
CPU4
Face Recognition4
Object4
Quantization4
Diagnostic3
Face Verification3
Network Pruning3
Object Recognition3
Privacy Preserving3

Usage over time archive 2025-07-28

Papers per year tagged with SqueezeNet: 2016 to 2025, peak 18 18 0 2016: 4 papers 2016 2017: 7 papers 2017 2018: 17 papers 2018 2019: 10 papers 2019 2020: 18 papers 2020 2021: 15 papers 2021 2022: 6 papers 2022 2023: 6 papers 2023 2024: 8 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (97 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

Light-weight neural networksConvolutional 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