Methods › Computer Vision › Image Model Blocks › Squeeze-and-Excitation Block

Squeeze-and-Excitation Block

543 papers tagged archive 2025-07-28

Introduced by Jie Hu et al. in Squeeze-and-Excitation Networks

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

The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature recalibration. The process is:

PaperSourceSee Code · osmr/imgclsmob

Papers archive 2025-07-28

30 shown of 543, 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 388 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
Image Classification119
image-classification78
Transfer Learning58
Object Detection54
Semantic Segmentation44
Classification42
Neural Architecture Search42
object-detection38
Data Augmentation31
General Classification29
Segmentation29
Deep Learning24
GPU20
Decoder19
Diagnostic19
Instance Segmentation17
Quantization14
Multi-Task Learning12
Computational Efficiency11
Image Segmentation11

Usage over time archive 2025-07-28

Papers per year tagged with Squeeze-and-Excitation Block: 2017 to 2025, peak 110 110 0 2017: 3 papers 2017 2018: 10 papers 2018 2019: 35 papers 2019 2020: 86 papers 2020 2021: 110 papers 2021 2022: 88 papers 2022 2023: 84 papers 2023 2024: 93 papers 2024 2025: 34 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (543 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

Image Model Blocks

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