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

Despite the growing success of Convolution neural networks (CNN) in therecent past in the task of scene segmentation, the standard models lack some ofthe important features that might result in sub-optimal segmentation outputs.The widely used encoder-decoder architecture extracts and uses severalredundant and low-level features at different steps and different scales. Also,these networks fail to map the long-range dependencies of local features, whichresults in discriminative feature maps corresponding to each semantic class inthe resulting segmented image. In this paper, we propose a novel multi-scaleattention network for scene segmentation purposes by using the rich contextualinformation from an image. Different from the original UNet architecture wehave used attention gates which take the features from the encoder and theoutput of the pyramid pool as input and produced out-put is furtherconcatenated with the up-sampled output of the previous pyramid-pool layer andmapped to the next subsequent layer. This network can map local features withtheir global counterparts with improved accuracy and emphasize ondiscriminative image regions by focusing on relevant local features only. Wealso propose a compound loss function by optimizing the IoU loss and fusingDice Loss and Weighted Cross-entropy loss with it to achieve an optimalsolution at a faster convergence rate. We have evaluated our model on twostandard datasets named PascalVOC2012 and ADE20k and was able to achieve meanIoU of 79.88% and 44.88% on the two datasets respectively, and compared ourresult with the widely known models to prove the superiority of our model overthem.

Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation