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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present an end-to-end trainable deep convolutional neural network (DCNN)for semantic segmentation with built-in awareness of semantically meaningfulboundaries. Semantic segmentation is a fundamental remote sensing task, andmost state-of-the-art methods rely on DCNNs as their workhorse. A major reasonfor their success is that deep networks learn to accumulate contextualinformation over very large windows (receptive fields). However, this successcomes at a cost, since the associated loss of effecive spatial resolutionwashes out high-frequency details and leads to blurry object boundaries. Here,we propose to counter this effect by combining semantic segmentation withsemantically informed edge detection, thus making class-boundaries explicit inthe model, First, we construct a comparatively simple, memory-efficient modelby adding boundary detection to the Segnet encoder-decoder architecture.Second, we also include boundary detection in FCN-type models and set up ahigh-end classifier ensemble. We show that boundary detection significantlyimproves semantic segmentation with CNNs. Our high-end ensemble achieves > 90%overall accuracy on the ISPRS Vaihingen benchmark.

Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection