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

In the semantic segmentation of street scenes the reliability of theprediction and therefore uncertainty measures are of highest interest. Wepresent a method that generates for each input image a hierarchy of nestedcrops around the image center and presents these, all re-scaled to the samesize, to a neural network for semantic segmentation. The resulting softmaxoutputs are then post processed such that we can investigate mean and varianceover all image crops as well as mean and variance of uncertainty heat mapsobtained from pixel-wise uncertainty measures, like the entropy, applied toeach crop's softmax output. In our tests, we use the publicly availableDeepLabv3+ MobilenetV2 network (trained on the Cityscapes dataset) anddemonstrate that the incorporation of crops improves the quality of theprediction and that we obtain more reliable uncertainty measures. These arethen aggregated over predicted segments for either classifying between IoU=0and IoU>0 (meta classification) or predicting the IoU via linear regression(meta regression). The latter yields reliable performance estimates forsegmentation networks, in particular useful in the absence of ground truth. Forthe task of meta classification we obtain a classification accuracy of$81.93\%$ and an AUROC of $89.89\%$. For meta regression we obtain an $R^2$value of $84.77\%$. These results yield significant improvements compared toother approaches.

Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Images