Methods › General › Activation Functions › Hard Swish

Hard Swish

90 papers tagged archive 2025-07-28

Introduced by Andrew Howard et al. in Searching for MobileNetV3

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

Hard Swish is a type of activation function based on Swish, but replaces the computationally expensive sigmoid with a piecewise linear analogue:

h-swish(x) = x(ReLU6(x+3))/6

PaperSourceSee Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 90, 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
Neural Architecture Search20
Image Classification16
Object Detection10
image-classification9
object-detection9
Segmentation7
Classification6
Decoder6
Quantization6
Transfer Learning6
Computational Efficiency5
Semantic Segmentation5
CPU4
Data Augmentation4
AutoML3
Bayesian Optimization3
Deep Learning3
GPU3
Diagnostic2
Diversity2

Usage over time archive 2025-07-28

Papers per year tagged with Hard Swish: 2019 to 2025, peak 18 18 0 2019: 7 papers 2019 2020: 12 papers 2020 2021: 17 papers 2021 2022: 18 papers 2022 2023: 16 papers 2023 2024: 13 papers 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (90 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

Activation Functions

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