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

We present a novel modular object detection convolutional neural network thatsignificantly improves the accuracy of object detection. The network consistsof two stages in a hierarchical structure. The first stage is a network thatdetects general classes. The second stage consists of separate networks torefine the classification and localization of each of the general classesobjects. Compared to a state of the art object detection networks theclassification error in the modular network is improved by approximately 3-5times, from 12% to 2.5 %-4.5%. This network is easy to implement and has a 0.94mAP. The network architecture can be a platform to improve the accuracy ofwidespread state of the art object detection networks and other kinds of deeplearning networks. We show that a deep learning network initialized by transferlearning becomes more accurate as the number of classes it later trained todetect becomes smaller.

Modular network for high accuracy object detection