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

Visual defect detection (VDD) for high-mix low-volume production ofnon-convex metal objects, such as high-pressure cylindrical piping joint parts(VDD-HPPPs), is challenging because subtle difference in domain (e.g., metalobjects, imaging device, viewpoints, lighting) significantly affects thespecular reflection characteristics of individual metal object types. In thispaper, we address this issue by introducing a tailor-made VDD framework thatcan be automatically adapted to a new domain. Specifically, we formulate thisadaptation task as the problem of network architecture search (NAS) on a deepobject-detection network, in which the network architecture is searched viareinforcement learning. We demonstrate the effectiveness of the proposedframework using the VDD-HPPPs task as a factory case study. Experimentalresults show that the proposed method achieved higher burr detection accuracycompared with the baseline method for data with different training/test domainsfor the non-convex HPPPs, which are particularly affected by domain shifts.

TaylorMade VDD: Domain-adaptive Visual Defect Detector for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects