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

Weakly-Supervised Semantic Segmentation (WSSS) segments objects without aheavy burden of dense annotation. While as a price, generated pseudo-masksexist obvious noisy pixels, which result in sub-optimal segmentation modelstrained over these pseudo-masks. But rare studies notice or work on thisproblem, even these noisy pixels are inevitable after their improvements onpseudo-mask. So we try to improve WSSS in the aspect of noise mitigation. Andwe observe that many noisy pixels are of high confidence, especially when theresponse range is too wide or narrow, presenting an uncertain status. Thus, inthis paper, we simulate noisy variations of response by scaling the predictionmap multiple times for uncertainty estimation. The uncertainty is then used toweight the segmentation loss to mitigate noisy supervision signals. We callthis method URN, abbreviated from Uncertainty estimation via Response scalingfor Noise mitigation. Experiments validate the benefits of URN, and our methodachieves state-of-the-art results at 71.2% and 41.5% on PASCAL VOC 2012 and MSCOCO 2014 respectively, without extra models like saliency detection. Code isavailable at https://github.com/XMed-Lab/URN.

Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation