CAT-EDNet: Cross-Attention Transformer-Based Encoder-Decoder Network for Salient Defect Detection of Strip Steel Surface

The morphologies of various surface defects on strip steel suffer from oil stain, water drops, steel textures, and erratic illumination. It is still challenging to recognize defect boundary precisely from cluttered backgrounds. This article emphasizes such a fact that skip connections between encode...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on instrumentation and measurement Ročník 71; s. 1 - 13
Hlavní autori: Luo, Qiwu, Su, Jiaojiao, Yang, Chunhua, Gui, Weihua, Silven, Olli, Liu, Li
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Automated visual inspection (AVI)
Coders
Decoding
encoder–decoder network (EDNet)
Entropy (Information theory)
Feature extraction
Inspection
salient detection
Steel
steel strip
Strip steel
Strips
Surface defects
transformer
Transformers
Visualization
Water drops
ISSN:0018-9456, 1557-9662
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The morphologies of various surface defects on strip steel suffer from oil stain, water drops, steel textures, and erratic illumination. It is still challenging to recognize defect boundary precisely from cluttered backgrounds. This article emphasizes such a fact that skip connections between encoder and decoder are not equally effective, attempts to adaptively allocate the aggregation weights that represent differentiated information entropy values in channelwise, by importing a stack of cross-attention transformer (CAT) into the encoder-decoder network (EDNet). Besides, a cross-attention refinement module (CARM) is constructed closely after the decoder to further optimize the coarse saliency maps. This newly nominated CAT-EDNet can well address the semantic gap issue among the multiscale features for its multihead attention structure. The CAT-EDNet performs best on insuring defect integrity and maintaining defect boundary details when compared with 12 state-of-the-arts, and the detection efficiency is at 28 fps even under the noise interfered scenario.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2022.3165270