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

Unlike existing fully-supervised approaches, we rethink colorectal polypsegmentation from an out-of-distribution perspective with a simple buteffective self-supervised learning approach. We leverage the ability of maskedautoencoders -- self-supervised vision transformers trained on a reconstructiontask -- to learn in-distribution representations; here, the distribution ofhealthy colon images. We then perform out-of-distribution reconstruction andinference, with feature space standardisation to align the latent distributionof the diverse abnormal samples with the statistics of the healthy samples. Wegenerate per-pixel anomaly scores for each image by calculating the differencebetween the input and reconstructed images and use this signal forout-of-distribution (ie, polyp) segmentation. Experimental results on sixbenchmarks show that our model has excellent segmentation performance andgeneralises across datasets. Our code is publicly available athttps://github.com/GewelsJI/Polyp-OOD.

Rethinking Polyp Segmentation from an Out-of-Distribution Perspective