Methods › Computer Vision › Pooling Operations › Global Average Pooling

Global Average Pooling

4,076 papers tagged archive 2025-07-28

Introduced by Min Lin et al. in Network In Network

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

Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding category of the classification task in the last mlpconv layer. Instead of adding fully connected layers on top of the feature maps, we take the average of each feature map, and the resulting vector is fed directly into the softmax layer.

One advantage of global average pooling over the fully connected layers is that it is more native to the convolution structure by enforcing correspondences between feature maps and categories. Thus the feature maps can be easily interpreted as categories confidence maps. Another advantage is that there is no parameter to optimize in the global average pooling thus overfitting is avoided at this layer. Furthermore, global average pooling sums out the spatial information, thus it is more robust to spatial translations of the input.

PaperSourceSee Code · pytorch/vision

Papers archive 2025-07-28

30 shown of 4,076, 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 1,096 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 Classification573
Object Detection465
image-classification437
object-detection414
Semantic Segmentation317
General Classification278
Transfer Learning274
Classification265
Object208
Segmentation207
Data Augmentation182
Self-Supervised Learning170
Representation Learning160
Contrastive Learning159
Deep Learning159
GPU125
Reinforcement Learning (RL)108
Neural Architecture Search106
Quantization100
Instance Segmentation97

Usage over time archive 2025-07-28

Papers per year tagged with Global Average Pooling: 2013 to 2025, peak 694 694 0 2013: 1 paper 2013 2014: 1 paper 2014 2015: 4 papers 2015 2016: 43 papers 2016 2017: 136 papers 2017 2018: 286 papers 2018 2019: 464 papers 2019 2020: 625 papers 2020 2021: 694 papers 2021 2022: 551 papers 2022 2023: 529 papers 2023 2024: 550 papers 2024 2025: 192 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (4,076 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