"SDDNet: A Fast and Accurate Network for Surface Defect Detection" by Lisha Cui, Xiaoheng Jiang et al.
This article proposes a fast and accurate network for surface defect detection, termed SDDNet. SDDNet mainly addresses two challenging issues - large texture variation and small size of defects - by introducing two modules: feature retaining block (FRB) and skip densely connected module (SDCM). FRB fuses multiple pyramidal feature maps with different resolutions and is plugged on the top of pooling layers, aiming to preserve the texture information, which may be lost because of downsampling. SDC...
Convolutional Neural Network Ultiscale Feature Maps Real Time Processing Small Defects Urface Defect Detection
Source: uow.edu.au