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

Saliency detection has been widely studied because it plays an important rolein various vision applications, but it is difficult to evaluate saliencysystems because each measure has its own bias. In this paper, we first revisitthe problem of applying the widely used saliency metrics on modernConvolutional Neural Networks(CNNs). Our investigation shows the saliencydatasets have been built based on different choices of parameters and CNNs aredesigned to fit a dataset-specific distribution. Secondly, we show that theShuffled Area Under Curve(S-AUC) metric still suffers from spatial biases. Wepropose a new saliency metric based on the AUC property, which aims at samplinga more directional negative set for evaluation, denoted as Farthest-NeighborAUC(FN-AUC). We also propose a strategy to measure the quality of the samplednegative set. Our experiment shows FN-AUC can measure spatial biases, centraland peripheral, more effectively than S-AUC without penalizing the fixationlocations. Thirdly, we propose a global smoothing function to overcome theproblem of few value degrees (output quantization) in computing AUC metrics.Comparing with random noise, our smooth function can create unique valueswithout losing the relative saliency relationship.

Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve