Methods › Computer Vision › Pooling Operations › Average Pooling

Average Pooling

5,125 papers tagged archive 2025-07-28

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

Average Pooling is a pooling operation that calculates the average value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually used after a convolutional layer. It adds a small amount of translation invariance - meaning translating the image by a small amount does not significantly affect the values of most pooled outputs. It extracts features more smoothly than Max Pooling, whereas max pooling extracts more pronounced features like edges.

Image Source: here

Papers archive 2025-07-28

30 shown of 5,125, 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 1,215 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
Image Classification716
image-classification551
Object Detection537
object-detection476
Semantic Segmentation448
Transfer Learning380
General Classification349
Classification342
Segmentation291
Object239
Data Augmentation223
Deep Learning211
Self-Supervised Learning178
Representation Learning171
Contrastive Learning166
GPU157
Quantization149
Neural Architecture Search138
Reinforcement Learning (RL)128
Diagnostic119

Usage over time archive 2025-07-28

Papers per year tagged with Average Pooling: 2013 to 2025, peak 879 879 0 2013: 1 paper 2013 2014: 5 papers 2014 2015: 18 papers 2015 2016: 69 papers 2016 2017: 164 papers 2017 2018: 342 papers 2018 2019: 550 papers 2019 2020: 765 papers 2020 2021: 879 papers 2021 2022: 707 papers 2022 2023: 677 papers 2023 2024: 705 papers 2024 2025: 243 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (5,125 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

Pooling Operations

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