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 this paper we present a novel loss function, called class-agnosticsegmentation (CAS) loss. With CAS loss the class descriptors are learned duringtraining of the network. We don't require to define the label of a classa-priori, rather the CAS loss clusters regions with similar appearance togetherin a weakly-supervised manner. Furthermore, we show that the CAS loss functionis sparse, bounded, and robust to class-imbalance. We first apply our CAS lossfunction with fully-convolutional ResNet101 and DeepLab-v3 architectures to thebinary segmentation problem of salient object detection. We investigate theperformance against the state-of-the-art methods in two settings of low andhigh-fidelity training data on seven salient object detection datasets. Forlow-fidelity training data (incorrect class label) class-agnostic segmentationloss outperforms the state-of-the-art methods on salient object detectiondatasets by staggering margins of around 50%. For high-fidelity training data(correct class labels) class-agnostic segmentation models perform as good asthe state-of-the-art approaches while beating the state-of-the-art methods onmost datasets. In order to show the utility of the loss function acrossdifferent domains we then also test on general segmentation dataset, whereclass-agnostic segmentation loss outperforms competing losses by huge margins.

Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation