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

Prevalent semantic segmentation solutions are, in essence, a densediscriminative classifier of p(class|pixel feature). Though straightforward,this de facto paradigm neglects the underlying data distribution p(pixelfeature|class), and struggles to identify out-of-distribution data. Goingbeyond this, we propose GMMSeg, a new family of segmentation models that relyon a dense generative classifier for the joint distribution p(pixelfeature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs)via Expectation-Maximization (EM), so as to capture class-conditionaldensities. Meanwhile, the deep dense representation is end-to-end trained in adiscriminative manner, i.e., maximizing p(class|pixel feature). This endowsGMMSeg with the strengths of both generative and discriminative models. With avariety of segmentation architectures and backbones, GMMSeg outperforms thediscriminative counterparts on three closed-set datasets. More impressively,without any modification, GMMSeg even performs well on open-world datasets. Webelieve this work brings fundamental insights into the related fields.

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models