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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recently salient object detection has witnessed remarkable improvement owingto the deep convolutional neural networks which can harvest powerful featuresfor images. In particular, state-of-the-art salient object detection methodsenjoy high accuracy and efficiency from fully convolutional network (FCN) basedframeworks which are trained from end to end and predict pixel-wise labels.However, such framework suffers from adversarial attacks which confuse neuralnetworks via adding quasi-imperceptible noises to input images without changingthe ground truth annotated by human subjects. To our knowledge, this paper isthe first one that mounts successful adversarial attacks on salient objectdetection models and verifies that adversarial samples are effective on a widerange of existing methods. Furthermore, this paper proposes a novel end-to-endtrainable framework to enhance the robustness for arbitrary FCN-based salientobject detection models against adversarial attacks. The proposed frameworkadopts a novel idea that first introduces some new generic noise to destroyadversarial perturbations, and then learns to predict saliency maps for inputimages with the introduced noise. Specifically, our proposed method consists ofa segment-wise shielding component, which preserves boundaries and destroysdelicate adversarial noise patterns and a context-aware restoration component,which refines saliency maps through global contrast modeling. Experimentalresults suggest that our proposed framework improves the performancesignificantly for state-of-the-art models on a series of datasets.

ROSA: Robust Salient Object Detection against Adversarial Attacks