.png){kind=icon}
.png){kind=icon}
Return
Progressive Feature Enhancement Network for Surface Defect Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TETCI.2024.3523770.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Surface defect detection is critical for maintaining the high quality of industrial products. However, defect detection is confronted with challenges, such as diverse defect types and scales, low contrast, and complex backgrounds. To tackle the problems, we propose a Progressive Feature Enhancement Network (PFENet), which aims to gradually strengthen the representation of features through semantic-guided Single-scale Feature Enhancement (SFE) module and Cross-scale Feature Enhancement (CFE) module. Specifically, SFE highlights defect semantic information of multi-level features by exploiting spatial similarities between the features and high-level features. CFE adaptively selects important defect information and suppresses redundant information through the mutual interaction of cross-level features. The mutual interaction enlarges the difference between foreground and background and facilitates learning more discriminative defect features for complex defects. Extensive experiments on three publicly available defect datasets, magnetic tile (MT), NEU-Seg, and Road defect dataset demonstrate that the proposed method achieves state-of-the-art performance.
Keywords:
Feature extraction
Semantics
Defect detection
Transformers
Computational modeling
Convolutional codes
Surface morphology
Shape
Neural networks
Interference
Cross-scale feature fusion
defect segmentation
feature enhancement
semantic guidance
Journal
I
IF:
6.5
Papers:
1.4K
Citations:
4.5K