Papers › Stochastic Subsampling With Average Pooling

Stochastic Subsampling With Average Pooling

25 Sep 2024arXiv:2409.16630archive 2025-07-28

Bum Jun Kim, Sang Woo Kim

Regularization of deep neural networks has been an important issue to achieve higher generalization performance without overfitting problems. Although the popular method of Dropout provides a regularization effect, it causes inconsistent properties in the output, which may degrade the performance of deep neural networks. In this study, we propose a new module called stochastic average pooling, which incorporates Dropout-like stochasticity in pooling. We describe the properties of stochastic subsampling and average pooling and leverage them to design a module without any inconsistency problem. The stochastic average pooling achieves a regularization effect without any potential performance degradation due to the inconsistency issue and can easily be plugged into existing architectures of deep neural networks. Experiments demonstrate that replacing existing average pooling with stochastic average pooling yields consistent improvements across a variety of tasks, datasets, and models.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fine-Grained Image ClassificationImage ClassificationObject DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification Caltech-101 SE-ResNet-101 (SAP) Top-1 Error Rate 15.949% #14 of 18 Archive leaderboard report
Fine-Grained Image Classification Oxford-IIIT Pets SE-ResNet-101 (SAP) Accuracy 86.011 #16 of 19 Archive leaderboard report
Image Classification CIFAR-10 ResNet-110 (SAP) Percentage correct 93.861 #167 of 265 Archive leaderboard report
Image Classification CIFAR-100 ResNet-110 (SAP) Percentage correct 72.537 #167 of 211 Archive leaderboard report
Image Classification Stanford Cars SE-ResNet-101 (SAP) Accuracy 85.812 #21 of 24 Archive leaderboard report
Object Detection COCO 2017 DyHead (SAP) AP 42.1 #6 of 24 Archive leaderboard report
Object Detection COCO 2017 DyHead (SAP) AP50 59.4 #6 of 24 Archive leaderboard report
Object Detection COCO 2017 DyHead (SAP) AP75 45.9 #6 of 24 Archive leaderboard report
Semantic Segmentation ISPRS Potsdam PSPNet (SAP) Mean IoU 74.3 #17 of 20 Archive leaderboard report
Semantic Segmentation ISPRS Potsdam PSPNet (SAP) Overall Accuracy 88.56 #17 of 20 Archive leaderboard report
Semantic Segmentation ISPRS Vaihingen UPerNet (SAP) Category mIoU 73.27 #10 of 12 Archive leaderboard report
Semantic Segmentation ISPRS Vaihingen UPerNet (SAP) Overall Accuracy 90.14 #10 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Average PoolingDropout

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