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

Semantic segmentation models classify pixels into a set of known(``in-distribution'') visual classes. When deployed in an open world, thereliability of these models depends on their ability not only to classifyin-distribution pixels but also to detect out-of-distribution (OoD) pixels.Historically, the poor OoD detection performance of these models has motivatedthe design of methods based on model re-training using synthetic trainingimages that include OoD visual objects. Although successful, these re-trainedmethods have two issues: 1) their in-distribution segmentation accuracy maydrop during re-training, and 2) their OoD detection accuracy does notgeneralise well to new contexts (e.g., country surroundings) outside thetraining set (e.g., city surroundings). In this paper, we mitigate these issueswith: (i) a new residual pattern learning (RPL) module that assists thesegmentation model to detect OoD pixels without affecting the inliersegmentation performance; and (ii) a novel context-robust contrastive learning(CoroCL) that enforces RPL to robustly detect OoD pixels among variouscontexts. Our approach improves by around 10\% FPR and 7\% AuPRC the previousstate-of-the-art in Fishyscapes, Segment-Me-If-You-Can, and RoadAnomalydatasets. Our code is available at: https://github.com/yyliu01/RPL.

Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation