Methods › Computer Vision › Convolutional Neural Networks › RegNetY

RegNetY

24 papers tagged archive 2025-07-28

Introduced by Ilija Radosavovic et al. in Designing Network Design Spaces

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

RegNetY is a convolutional network design space with simple, regular models with parameters: depth d, initial width w₀ > 0, and slope wₐ > 0, and generates a different block width uⱼ for each block j < d. The key restriction for the RegNet types of model is that there is a linear parameterisation of block widths (the design space only contains models with this linear structure):

uⱼ = w₀ + wₐ·j

For RegNetX we have additional restrictions: we set b = 1 (the bottleneck ratio), 12 ≤d ≤28, and wₘ ≥2 (the width multiplier).

For RegNetY we make one change, which is to include Squeeze-and-Excitation blocks.

PaperSourceSee Code · facebookresearch/pycls

Papers archive 2025-07-28

24 shown of 24, 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 49 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
Survival Analysis5
Image Classification4
Prognosis4
Decoder3
Reinforcement Learning3
Transfer Learning3
reinforcement-learning3
BIG-bench Machine Learning2
Epidemiology2
Federated Learning2
Question Answering2
Reinforcement Learning (RL)2
Adversarial Attack1
Atari Games1
Chunking1
Classification1
Computational Efficiency1
Coronary Artery Segmentation1
Data Augmentation1
Deep Reinforcement Learning1

Usage over time archive 2025-07-28

Papers per year tagged with RegNetY: 2020 to 2025, peak 6 6 0 2020: 3 papers 2020 2021: 6 papers 2021 2022: 2 papers 2022 2023: 5 papers 2023 2024: 4 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (24 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