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

Neural architecture search has proven to be highly effective in the design ofefficient convolutional neural networks that are better suited for mobiledeployment than hand-designed networks. Hypothesizing that neural architecturesearch holds great potential for human pose estimation, we explore theapplication of neuroevolution, a form of neural architecture search inspired bybiological evolution, in the design of 2D human pose networks for the firsttime. Additionally, we propose a new weight transfer scheme that enables us toaccelerate neuroevolution in a flexible manner. Our method produces networkdesigns that are more efficient and more accurate than state-of-the-arthand-designed networks. In fact, the generated networks process images athigher resolutions using less computation than previous hand-designed networksat lower resolutions, allowing us to push the boundaries of 2D human poseestimation. Our base network designed via neuroevolution, which we refer to asEvoPose2D-S, achieves comparable accuracy to SimpleBaseline while being 50%faster and 12.7x smaller in terms of file size. Our largest network,EvoPose2D-L, achieves new state-of-the-art accuracy on the Microsoft COCOKeypoints benchmark, is 4.3x smaller than its nearest competitor, and hassimilar inference speed. The code is publicly available athttps://github.com/wmcnally/evopose2d.

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation Using Accelerated Neuroevolution With Weight Transfer