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/

Zendy Plus

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

Zendy Tools

Zendy Open

Adversarial robustness has been studied extensively in image classification,especially for the $\ell_\infty$-threat model, but significantly less so forrelated tasks such as object detection and semantic segmentation, where attacksturn out to be a much harder optimization problem than for imageclassification. We propose several problem-specific novel attacks minimizingdifferent metrics in accuracy and mIoU. The ensemble of our attacks, SEA, showsthat existing attacks severely overestimate the robustness of semanticsegmentation models. Surprisingly, existing attempts of adversarial trainingfor semantic segmentation models turn out to be weak or even completelynon-robust. We investigate why previous adaptations of adversarial training tosemantic segmentation failed and show how recently proposed robust ImageNetbackbones can be used to obtain adversarially robust semantic segmentationmodels with up to six times less training time for PASCAL-VOC and the morechallenging ADE20k. The associated code and robust models are available athttps://github.com/nmndeep/robust-segmentation

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models