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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we present a comprehensive study on semantic segmentation withthe Pascal VOC dataset. Here, we have to label each pixel with a class which inturn segments the entire image based on the objects/entities present. To tacklethis, we firstly use a Fully Convolution Network (FCN) baseline which gave71.31% pixel accuracy and 0.0527 mean IoU. We analyze its performance andworking and subsequently address the issues in the baseline with threeimprovements: a) cosine annealing learning rate scheduler(pixel accuracy:72.86%, IoU: 0.0529), b) data augmentation(pixel accuracy: 69.88%, IoU: 0.0585)c) class imbalance weights(pixel accuracy: 68.98%, IoU: 0.0596). Apart fromthese changes in training pipeline, we also explore three differentarchitectures: a) Our proposed model -- Advanced FCN (pixel accuracy: 67.20%,IoU: 0.0602) b) Transfer Learning with ResNet (Best performance) (pixelaccuracy: 71.33%, IoU: 0.0926 ) c) U-Net(pixel accuracy: 72.15%, IoU: 0.0649).We observe that the improvements help in greatly improving the performance, asreflected both, in metrics and segmentation maps. Interestingly, we observethat among the improvements, dataset augmentation has the greatestcontribution. Also, note that transfer learning model performs the best on thepascal dataset. We analyse the performance of these using loss, accuracy andIoU plots along with segmentation maps, which help us draw valuable insightsabout the working of the models.

Exploiting CNNs for Semantic Segmentation with Pascal VOC