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 recent years, deep neural networks have defined the state-of-the-art insemantic segmentation where their predictions are constrained to a predefinedset of semantic classes. They are to be deployed in applications such asautomated driving, although their categorically confined expressive power runscontrary to such open world scenarios. Thus, the detection and segmentation ofobjects from outside their predefined semantic space, i.e., out-of-distribution(OoD) objects, is of highest interest. Since uncertainty estimation methodslike softmax entropy or Bayesian models are sensitive to erroneous predictions,these methods are a natural baseline for OoD detection. Here, we present amethod for obtaining uncertainty scores from pixel-wise loss gradients whichcan be computed efficiently during inference. Our approach is simple toimplement for a large class of models, does not require any additional trainingor auxiliary data and can be readily used on pre-trained segmentation models.Our experiments show the ability of our method to identify wrong pixelclassifications and to estimate prediction quality at negligible computationaloverhead. In particular, we observe superior performance in terms of OoDsegmentation to comparable baselines on the SegmentMeIfYouCan benchmark,clearly outperforming other methods.

Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation