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

In recent years, how to strike a good trade-off between accuracy andinference speed has become the core issue for real-time semantic segmentationapplications, which plays a vital role in real-world scenarios such asautonomous driving systems and drones. In this study, we devise a novellightweight network using a multi-scale context fusion (MSCFNet) scheme, whichexplores an asymmetric encoder-decoder architecture to dispose this problem.More specifically, the encoder adopts some developed efficient asymmetricresidual (EAR) modules, which are composed of factorization depth-wiseconvolution and dilation convolution. Meanwhile, instead of complicatedcomputation, simple deconvolution is applied in the decoder to further reducethe amount of parameters while still maintaining high segmentation accuracy.Also, MSCFNet has branches with efficient attention modules from differentstages of the network to well capture multi-scale contextual information. Thenwe combine them before the final classification to enhance the expression ofthe features and improve the segmentation efficiency. Comprehensive experimentson challenging datasets have demonstrated that the proposed MSCFNet, whichcontains only 1.15M parameters, achieves 71.9\% Mean IoU on the Cityscapestesting dataset and can run at over 50 FPS on a single Titan XP GPUconfiguration.

MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation