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

Current NAS-based semantic segmentation methods focus on accuracyimprovements rather than light-weight design. In this paper, we proposed atwo-stage framework to design our NAS-based RSPNet model for light-weightsemantic segmentation. The first architecture search determines the inner cellstructure, and the second architecture search considers exponentially growingpaths to finalize the outer structure of the network. It was shown in theliterature that the fusion of high- and low-resolution feature maps producesstronger representations. To find the expected macro structure without manualdesign, we adopt a new path-attention mechanism to efficiently search forsuitable paths to fuse useful information for better segmentation. Our searchfor repeatable micro-structures from cells leads to a superior networkarchitecture in semantic segmentation. In addition, we propose an RSP(recursive Stage Partial) architecture to search a light-weight design forNAS-based semantic segmentation. The proposed architecture is very efficient,simple, and effective that both the macro- and micro- structure searches can becompleted in five days of computation on two V100 GPUs. The light-weight NASarchitecture with only 1/4 parameter size of SoTA architectures can achieveSoTA performance on semantic segmentation on the Cityscapes dataset withoutusing any backbones.

NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation