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

Surface defect inspection is an important task in industrial inspection. Deeplearning-based methods have demonstrated promising performance in this domain.Nevertheless, these methods still suffer from misjudgment when encounteringchallenges such as low-contrast defects and complex backgrounds. To overcomethese issues, we present a decision fusion network (DFNet) that incorporatesthe semantic decision with the feature decision to strengthen the decisionability of the network. In particular, we introduce a decision fusion module(DFM) that extracts a semantic vector from the semantic decision branch and afeature vector for the feature decision branch and fuses them to make the finalclassification decision. In addition, we propose a perception fine-tuningmodule (PFM) that fine-tunes the foreground and background during thesegmentation stage. PFM generates the semantic and feature outputs that aresent to the classification decision stage. Furthermore, we present aninner-outer separation weight matrix to address the impact of label edgeuncertainty during segmentation supervision. Our experimental results on thepublicly available datasets including KolektorSDD2 (96.1% AP) andMagnetic-tile-defect-datasets (94.6% mAP) demonstrate the effectiveness of theproposed method.

Decision Fusion Network with Perception Fine-tuning for Defect Classification