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

Smoke segmentation is essential to precisely localize wildfire so that it canbe extinguished in an early phase. Although deep neural networks have achievedpromising results on image segmentation tasks, they are prone to beoverconfident for smoke segmentation due to its non-rigid shape and transparentappearance. This is caused by both knowledge level uncertainty due to limitedtraining data for accurate smoke segmentation and labeling level uncertaintyrepresenting the difficulty in labeling ground-truth. To effectively model thetwo types of uncertainty, we introduce a Bayesian generative model tosimultaneously estimate the posterior distribution of model parameters and itspredictions. Further, smoke images suffer from low contrast and ambiguity,inspired by physics-based image dehazing methods, we design atransmission-guided local coherence loss to guide the network to learnpair-wise relationships based on pixel distance and the transmission feature.To promote the development of this field, we also contribute a high-qualitysmoke segmentation dataset, SMOKE5K, consisting of 1,400 real and 4,000synthetic images with pixel-wise annotation. Experimental results on benchmarktesting datasets illustrate that our model achieves both accurate predictionsand reliable uncertainty maps representing model ignorance about itsprediction. Our code and dataset are publicly available at:https://github.com/redlessme/Transmission-BVM.

Transmission-Guided Bayesian Generative Model for Smoke Segmentation