English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Convolutional neural networks (CNNs) have demonstrated remarkable results inimage classification for benchmark tasks and practical applications. The CNNswith deeper architectures have achieved even higher performance recently thanksto their robustness to the parallel shift of objects in images as well as theirnumerous parameters and the resulting high expression ability. However, CNNshave a limited robustness to other geometric transformations such as scalingand rotation. This limits the performance improvement of the deep CNNs, butthere is no established solution. This study focuses on scale transformationand proposes a network architecture called the weight-shared multi-stagenetwork (WSMS-Net), which consists of multiple stages of CNNs. The proposedWSMS-Net is easily combined with existing deep CNNs such as ResNet and DenseNetand enables them to acquire robustness to object scaling. Experimental resultson the CIFAR-10, CIFAR-100, and ImageNet datasets demonstrate that existingdeep CNNs combined with the proposed WSMS-Net achieve higher accuracies forimage classification tasks with only a minor increase in the number ofparameters and computation time.

A Novel Weight-Shared Multi-Stage CNN for Scale Robustness