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

Dense regression is a widely used approach in computer vision for tasks suchas image super-resolution, enhancement, depth estimation, etc. However, thehigh cost of annotation and labeling makes it challenging to achieve accurateresults. We propose incorporating active learning into dense regression modelsto address this problem. Active learning allows models to select the mostinformative samples for labeling, reducing the overall annotation cost whileimproving performance. Despite its potential, active learning has not beenwidely explored in high-dimensional computer vision regression tasks likesuper-resolution. We address this research gap and propose a new frameworkcalled USIM-DAL that leverages the statistical properties of colour images tolearn informative priors using probabilistic deep neural networks that modelthe heteroscedastic predictive distribution allowing uncertaintyquantification. Moreover, the aleatoric uncertainty from the network serves asa proxy for error that is used for active learning. Our experiments on a widevariety of datasets spanning applications in natural images (visual genome,BSD100), medical imaging (histopathology slides), and remote sensing (satelliteimages) demonstrate the efficacy of the newly proposed USIM-DAL and superiorityover several dense regression active learning methods.

USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution