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

Pixel-wise image segmentation is demanding task in computer vision. ClassicalU-Net architectures composed of encoders and decoders are very popular forsegmentation of medical images, satellite images etc. Typically, neural networkinitialized with weights from a network pre-trained on a large data set likeImageNet shows better performance than those trained from scratch on a smalldataset. In some practical applications, particularly in medicine and trafficsafety, the accuracy of the models is of utmost importance. In this paper, wedemonstrate how the U-Net type architecture can be improved by the use of thepre-trained encoder. Our code and corresponding pre-trained weights arepublicly available at https://github.com/ternaus/TernausNet. We compare threeweight initialization schemes: LeCun uniform, the encoder with weights fromVGG11 and full network trained on the Carvana dataset. This networkarchitecture was a part of the winning solution (1st out of 735) in the Kaggle:Carvana Image Masking Challenge.

TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation