Methods › Computer Vision › Pooling Operations › Global Average Pooling
Global Average Pooling
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.
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.
-
Automated MRI Tumor Segmentation using hybrid U-Net with Transformer and Efficient Attention 18 Jun 2025 · 0 repositories · arXiv:2506.15562
-
Detecting immune cells with label-free two-photon autofluorescence and deep learning 17 Jun 2025 · 0 repositories · arXiv:2506.14449
-
Deploying and Evaluating Multiple Deep Learning Models on Edge Devices for Diabetic Retinopathy Detection 14 Jun 2025 · 0 repositories · arXiv:2506.14834
-
SecONNds: Secure Outsourced Neural Network Inference on ImageNet 13 Jun 2025 · 2 repositories · arXiv:2506.11586
-
Circumventing Backdoor Space via Weight Symmetry 9 Jun 2025 · 1 repository · arXiv:2506.07467
-
Analyzing Breast Cancer Survival Disparities by Race and Demographic Location: A Survival Analysis Approach 8 Jun 2025 · 0 repositories · arXiv:2506.07191
-
Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning 6 Jun 2025 · 1 repository · arXiv:2506.05968Syntology ran 1 of 4 samples · 3 unverified
-
Synthetic Speech Source Tracing using Metric Learning 3 Jun 2025 · 0 repositories · arXiv:2506.02590
-
PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edge 31 May 2025 · 0 repositories · arXiv:2506.00438
-
ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation 30 May 2025 · 0 repositories · arXiv:2505.24481
-
Optimal Weighted Convolution for Classification and Denosing 30 May 2025 · 2 repositories · arXiv:2505.24558
-
Stepsize anything: A unified learning rate schedule for budgeted-iteration training 30 May 2025 · 0 repositories · arXiv:2505.24452
-
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition 29 May 2025 · 0 repositories · arXiv:2505.22985
-
Leveraging Diffusion Models for Synthetic Data Augmentation in Protein Subcellular Localization Classification 28 May 2025 · 0 repositories · arXiv:2505.22926
-
Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea 27 May 2025 · 0 repositories · arXiv:2505.20615
-
Lung Nodule Segmentation: Exploring Data Efficiency and Advanced Architectures 26 May 2025 · 0 repositories
-
Structured Initialization for Vision Transformers 26 May 2025 · 0 repositories · arXiv:2505.19985
-
Hierarchical-embedding autoencoder with a predictor (HEAP) as efficient architecture for learning long-term evolution of complex multi-scale physical systems 24 May 2025 · 0 repositories · arXiv:2505.18857
-
SW-ViT: A Spatio-Temporal Vision Transformer Network with Post Denoiser for Sequential Multi-Push Ultrasound Shear Wave Elastography 24 May 2025 · 0 repositories · arXiv:2505.18865
-
DECT-based Space-Squeeze Method for Multi-Class Classification of Metastatic Lymph Nodes in Breast Cancer 23 May 2025 · 1 repository · arXiv:2505.17528
-
EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion 23 May 2025 · 0 repositories · arXiv:2505.17367
-
The Cell Must Go On: Agar.io for Continual Reinforcement Learning 23 May 2025 · 1 repository · arXiv:2505.18347
-
Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting 22 May 2025 · 0 repositories · arXiv:2505.16513
-
Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare 22 May 2025 · 0 repositories · arXiv:2505.16190
-
SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models 22 May 2025 · 0 repositories · arXiv:2505.16318
-
An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI 21 May 2025 · 0 repositories · arXiv:2505.16033
-
Analysis of ABC Frontend Audio Systems for the NIST-SRE24 21 May 2025 · 0 repositories · arXiv:2505.15320
-
Comprehensive Lung Disease Detection Using Deep Learning Models and Hybrid Chest X-ray Data with Explainable AI 21 May 2025 · 0 repositories · arXiv:2505.16028
-
Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers 21 May 2025 · 0 repositories · arXiv:2505.15239
-
Unified Cross-Modal Attention-Mixer Based Structural-Functional Connectomics Fusion for Neuropsychiatric Disorder Diagnosis 21 May 2025 · 0 repositories · arXiv:2505.15139
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.
| Task | Papers |
|---|---|
| Image Classification | 573 |
| Object Detection | 465 |
| image-classification | 437 |
| object-detection | 414 |
| Semantic Segmentation | 317 |
| General Classification | 278 |
| Transfer Learning | 274 |
| Classification | 265 |
| Object | 208 |
| Segmentation | 207 |
| Data Augmentation | 182 |
| Self-Supervised Learning | 170 |
| Representation Learning | 160 |
| Contrastive Learning | 159 |
| Deep Learning | 159 |
| GPU | 125 |
| Reinforcement Learning (RL) | 108 |
| Neural Architecture Search | 106 |
| Quantization | 100 |
| Instance Segmentation | 97 |
Usage over time archive 2025-07-28
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
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