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 propose a method for high-performance semantic image segmentation (orsemantic pixel labelling) based on very deep residual networks, which achievesthe state-of-the-art performance. A few design factors are carefully consideredto this end.  We make the following contributions. (i) First, we evaluate differentvariations of a fully convolutional residual network so as to find the bestconfiguration, including the number of layers, the resolution of feature maps,and the size of field-of-view. Our experiments show that further enlarging thefield-of-view and increasing the resolution of feature maps are typicallybeneficial, which however inevitably leads to a higher demand for GPU memories.To walk around the limitation, we propose a new method to simulate a highresolution network with a low resolution network, which can be applied duringtraining and/or testing. (ii) Second, we propose an online bootstrapping methodfor training. We demonstrate that online bootstrapping is critically importantfor achieving good accuracy. (iii) Third we apply the traditional dropout tosome of the residual blocks, which further improves the performance. (iv)Finally, our method achieves the currently best mean intersection-over-union78.3\% on the PASCAL VOC 2012 dataset, as well as on the recent datasetCityscapes.

High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks