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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multimodal semantic segmentation is developing rapidly, but the modality ofRGB-Polarization remains underexplored. To delve into this problem, weconstruct a UPLight RGB-P segmentation benchmark with 12 typical underwatersemantic classes. In this work, we design the ShareCMP, an RGB-P semanticsegmentation framework with a shared dual-branch architecture, which reducesthe number of parameters by about 26-33% compared to previous dual-branchmodels. It encompasses a Polarization Generate Attention (PGA) module designedto generate polarization modal images with richer polarization properties forthe encoder. In addition, we introduce the Class Polarization-Aware Loss(CPALoss) to improve the learning and understanding of the encoder forpolarization modal information and to optimize the PGA module. With extensiveexperiments on a total of three RGB-P benchmarks, our ShareCMP achievesstate-of-the-art performance in mIoU with fewer parameters on the UPLight(92.45(+0.32)%), ZJU (92.7(+0.1)%), and MCubeS (50.99(+1.51)%) datasetscompared to the previous best methods. The code is available athttps://github.com/LEFTeyex/ShareCMP.

ShareCMP: Polarization-Aware RGB-P Semantic Segmentation