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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep convolutional neural networks (CNNs) have been widely used in surfacedefect detection. However, no CNN architecture is suitable for all detectiontasks and designing effective task-specific requires considerable effort. Theneural architecture search (NAS) technology makes it possible to automaticallygenerate adaptive data-driven networks. Here, we propose a new method calledNAS-ASDet to adaptively design network for surface defect detection. First, arefined and industry-appropriate search space that can adaptively adjust thefeature distribution is designed, which consists of repeatedly stacked basicnovel cells with searchable attention operations. Then, a progressive searchstrategy with a deep supervision mechanism is used to explore the search spacefaster and better. This method can design high-performance and lightweightdefect detection networks with data scarcity in industrial scenarios. Theexperimental results on four datasets demonstrate that the proposed methodachieves superior performance and a relatively lighter model size compared toother competitive methods, including both manual and NAS-based approaches.

NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search