Methods › General › Activation Functions › CReLU

CReLU

9 papers tagged archive 2025-07-28

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

CReLU, or Concatenated Rectified Linear Units, is a type of activation function which preserves both positive and negative phase information while enforcing non-saturated non-linearity. We compute by concatenating the layer output h as:

[ReLU(h), ReLU(-h)]

Source: Understanding and Improving Convolutional Neural...See Code · gist.github.com/lintangsutawika/f2f3fb422d6d7df28bd74e26940da2e6

Papers archive 2025-07-28

9 shown of 9, 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.

Diffusion Models Beat GANs on Image Classification
17 Jul 2023 · 1 repository · arXiv:2307.08702
Proper Straight-Through Estimator: Breaking symmetry promotes convergence to true minimum
29 Sep 2021 · 0 repositories
Neural Networks with Complex-Valued Weights Have No Spurious Local Minima
31 Jan 2021 · 0 repositories · arXiv:2103.07287
Complex neural networks have no spurious local minima
1 Jan 2021 · 0 repositories
Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
26 Aug 2020 · 1 repository · arXiv:2008.11434
Object Segmentation Without Labels with Large-Scale Generative Models
8 Jun 2020 · 1 repository · arXiv:2006.04988
Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN
31 Jan 2020 · 0 repositories · arXiv:2001.11761
Large Scale Adversarial Representation Learning
4 Jul 2019 · 4 repositories · arXiv:1907.02544

Syntology ran 0 of 3 samples · 3 unverified
Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units
16 Mar 2016 · 2 repositories · arXiv:1603.05201

Tasks archive 2025-07-28

20 shown of 26 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Image Classification	2
Image Generation	2
image-classification	2
Attribute	1
Classification	1
Contrastive Learning	1
Denoising	1
Fine-Grained Image Classification	1
GPU	1
Generative Adversarial Network	1
Image Enhancement	1
Image Reconstruction	1
Low-Light Image Enhancement	1
Object	1
Representation Learning	1
Saliency Detection	1
Segmentation	1
Self-Supervised Image Classification	1
Self-Supervised Learning	1
Semantic Segmentation	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (9 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