Methods › General › Activation Functions › ReLU6

ReLU6

95 papers tagged archive 2025-07-28

Introduced by Andrew G. Howard et al. in MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

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

ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased robustness when used with low-precision computation.

Image Credit: PyTorch

PaperSourceSee Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 95, 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 95 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 Classification19
Object Detection11
image-classification11
object-detection9
Segmentation7
Classification6
Computational Efficiency6
Decoder6
Quantization6
Semantic Segmentation6
Transfer Learning6
CPU4
Data Augmentation4
AutoML3
Bayesian Optimization3
Deep Learning3
GPU3
Image Segmentation3
Diagnostic2

Usage over time archive 2025-07-28

Papers per year tagged with ReLU6: 2018 to 2025, peak 19 19 0 2018: 1 paper 2018 2019: 7 papers 2019 2020: 12 papers 2020 2021: 19 papers 2021 2022: 18 papers 2022 2023: 17 papers 2023 2024: 13 papers 2024 2025: 8 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (95 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