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

Monocular depth estimation and semantic segmentation are two fundamentalgoals of scene understanding. Due to the advantages of task interaction, manyworks study the joint task learning algorithm. However, most existing methodsfail to fully leverage the semantic labels, ignoring the provided contextstructures and only using them to supervise the prediction of segmentationsplit, which limit the performance of both tasks. In this paper, we propose anetwork injected with contextual information (CI-Net) to solve the problem.Specifically, we introduce self-attention block in the encoder to generateattention map. With supervision from the ideal attention map created bysemantic label, the network is embedded with contextual information so that itcould understand scene better and utilize correlated features to make accurateprediction. Besides, a feature sharing module is constructed to make thetask-specific features deeply fused and a consistency loss is devised to makethe features mutually guided. We evaluate the proposed CI-Net on theNYU-Depth-v2 and SUN-RGBD datasets. The experimental results validate that ourproposed CI-Net could effectively improve the accuracy of semantic segmentationand depth estimation.

CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation