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

As designing appropriate Convolutional Neural Network (CNN) architecture inthe context of a given application usually involves heavy human works ornumerous GPU hours, the research community is soliciting thearchitecture-neutral CNN structures, which can be easily plugged into multiplemature architectures to improve the performance on our real-world applications.We propose Asymmetric Convolution Block (ACB), an architecture-neutralstructure as a CNN building block, which uses 1D asymmetric convolutions tostrengthen the square convolution kernels. For an off-the-shelf architecture,we replace the standard square-kernel convolutional layers with ACBs toconstruct an Asymmetric Convolutional Network (ACNet), which can be trained toreach a higher level of accuracy. After training, we equivalently convert theACNet into the same original architecture, thus requiring no extra computationsanymore. We have observed that ACNet can improve the performance of variousmodels on CIFAR and ImageNet by a clear margin. Through further experiments, weattribute the effectiveness of ACB to its capability of enhancing the model'srobustness to rotational distortions and strengthening the central skeletonparts of square convolution kernels.

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks