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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, deep learning has achieved great success in many computervision applications. Convolutional neural networks (CNNs) have lately emergedas a major approach to image classification. Most research on CNNs thus far hasfocused on developing architectures such as the Inception and residualnetworks. The convolution layer is the core of the CNN, but few studies haveaddressed the convolution unit itself. In this paper, we introduce aconvolution unit called the active convolution unit (ACU). A new convolutionhas no fixed shape, because of which we can define any form of convolution. Itsshape can be learned through backpropagation during training. Our proposed unithas a few advantages. First, the ACU is a generalization of convolution; it candefine not only all conventional convolutions, but also convolutions withfractional pixel coordinates. We can freely change the shape of theconvolution, which provides greater freedom to form CNN structures. Second, theshape of the convolution is learned while training and there is no need to tuneit by hand. Third, the ACU can learn better than a conventional unit, where weobtained the improvement simply by changing the conventional convolution to anACU. We tested our proposed method on plain and residual networks, and theresults showed significant improvement using our method on various datasets andarchitectures in comparison with the baseline.

Active Convolution: Learning the Shape of Convolution for Image Classification