Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309585905> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4309585905 abstract "Visual anomaly detection plays a significant role in the development of industrial automatic product quality inspection. As a result of the utmost imbalance in the amount of normal and abnormal data, growing attention has been given to unsupervised methods for defect detection. Although existing reconstruction-based methods have been widely studied recently, establishing a robust reconstruction model for various textured surface defect detection remains a challenging task due to homogeneous and nonregular surface textures. In this paper, we propose a novel unsupervised reconstruction-based method called the normal reference attention and defective feature perception network (NDP-Net) to accurately inspect a variety of textured defects. Unlike most reconstruction-based methods, our NDP-Net first employs an encoding module that extracts multi scale discriminative features of the surface textures, which is augmented with the defect discriminative ability by the proposed artificial defects and the novel pixel-level defect perception loss. Subsequently, a novel reference-based attention module (RBAM) is proposed to leverage the normal features of the fixed reference image to repair the defective features and restrain the reconstruction of the defects. Next, the repaired features are fed into a decoding module to reconstruct the normal textured background. Finally, the novel multi scale defect segmentation module (MSDSM) is introduced for precise defect detection and segmentation. In addition, a two-stage training strategy is utilized to enhance the inspection performance." @default.
- W4309585905 created "2022-11-28" @default.
- W4309585905 creator A5028340183 @default.
- W4309585905 creator A5058144230 @default.
- W4309585905 creator A5065172118 @default.
- W4309585905 creator A5076153623 @default.
- W4309585905 date "2022-11-18" @default.
- W4309585905 modified "2023-09-25" @default.
- W4309585905 title "Normal Reference Attention and Defective Feature Perception Network for Surface Defect Detection" @default.
- W4309585905 doi "https://doi.org/10.48550/arxiv.2211.10060" @default.
- W4309585905 hasPublicationYear "2022" @default.
- W4309585905 type Work @default.
- W4309585905 citedByCount "0" @default.
- W4309585905 crossrefType "posted-content" @default.
- W4309585905 hasAuthorship W4309585905A5028340183 @default.
- W4309585905 hasAuthorship W4309585905A5058144230 @default.
- W4309585905 hasAuthorship W4309585905A5065172118 @default.
- W4309585905 hasAuthorship W4309585905A5076153623 @default.
- W4309585905 hasBestOaLocation W43095859051 @default.
- W4309585905 hasConcept C11413529 @default.
- W4309585905 hasConcept C138885662 @default.
- W4309585905 hasConcept C153083717 @default.
- W4309585905 hasConcept C153180895 @default.
- W4309585905 hasConcept C154945302 @default.
- W4309585905 hasConcept C160633673 @default.
- W4309585905 hasConcept C2776401178 @default.
- W4309585905 hasConcept C31972630 @default.
- W4309585905 hasConcept C41008148 @default.
- W4309585905 hasConcept C41895202 @default.
- W4309585905 hasConcept C57273362 @default.
- W4309585905 hasConcept C89600930 @default.
- W4309585905 hasConcept C97931131 @default.
- W4309585905 hasConceptScore W4309585905C11413529 @default.
- W4309585905 hasConceptScore W4309585905C138885662 @default.
- W4309585905 hasConceptScore W4309585905C153083717 @default.
- W4309585905 hasConceptScore W4309585905C153180895 @default.
- W4309585905 hasConceptScore W4309585905C154945302 @default.
- W4309585905 hasConceptScore W4309585905C160633673 @default.
- W4309585905 hasConceptScore W4309585905C2776401178 @default.
- W4309585905 hasConceptScore W4309585905C31972630 @default.
- W4309585905 hasConceptScore W4309585905C41008148 @default.
- W4309585905 hasConceptScore W4309585905C41895202 @default.
- W4309585905 hasConceptScore W4309585905C57273362 @default.
- W4309585905 hasConceptScore W4309585905C89600930 @default.
- W4309585905 hasConceptScore W4309585905C97931131 @default.
- W4309585905 hasLocation W43095859051 @default.
- W4309585905 hasOpenAccess W4309585905 @default.
- W4309585905 hasPrimaryLocation W43095859051 @default.
- W4309585905 hasRelatedWork W1971623867 @default.
- W4309585905 hasRelatedWork W1982770690 @default.
- W4309585905 hasRelatedWork W2090093270 @default.
- W4309585905 hasRelatedWork W2124132578 @default.
- W4309585905 hasRelatedWork W2136485282 @default.
- W4309585905 hasRelatedWork W2404514746 @default.
- W4309585905 hasRelatedWork W2510758617 @default.
- W4309585905 hasRelatedWork W2546871836 @default.
- W4309585905 hasRelatedWork W2739874619 @default.
- W4309585905 hasRelatedWork W2970216048 @default.
- W4309585905 isParatext "false" @default.
- W4309585905 isRetracted "false" @default.
- W4309585905 workType "article" @default.