Methods › General › Normalization › Local Response Normalization

Local Response Normalization

421 papers tagged archive 2025-07-28

Introduced by Alex Krizhevsky et al. in ImageNet Classification with Deep Convolutional Neural Networks

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

Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the phenomenon of an excited neuron inhibiting its neighbours: this leads to a peak in the form of a local maximum, creating contrast in that area and increasing sensory perception. In practice, we can either normalize within the same channel or normalize across channels when we apply LRN to convolutional neural networks.

b_c = a_c(k + α/n∑_(c′=max(0, c-n/2))^(min(N-1,c+n/2))a_(c′)²)^(-β)

Where the size is the number of neighbouring channels used for normalization, α is multiplicative factor, β an exponent and k an additive factor

PaperSourceSee Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 421, 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 245 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
General Classification68
Image Classification52
image-classification46
Quantization45
Classification37
Object Detection34
Transfer Learning31
object-detection31
Deep Learning28
GPU28
Object25
Object Recognition25
Data Augmentation15
Model Compression14
CPU11
Clustering11
Network Pruning10
Representation Learning10
Diagnostic8
Retrieval8

Usage over time archive 2025-07-28

Papers per year tagged with Local Response Normalization: 2012 to 2025, peak 89 89 0 2012: 1 paper 2012 2013: 0 papers 2013 2014: 6 papers 2014 2015: 25 papers 2015 2016: 41 papers 2016 2017: 61 papers 2017 2018: 85 papers 2018 2019: 89 papers 2019 2020: 47 papers 2020 2021: 17 papers 2021 2022: 10 papers 2022 2023: 16 papers 2023 2024: 17 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (421 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

Normalization

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