Loss function comparison experiments.

<div><p>Aiming at the current problems in the field of industrial defect segmentation, such as difficulty of obtaining a large number of defect samples, low recognition accuracy and lack of segmentation accuracy, a surface defect segmentation model for aluminum based on feature different...

Full description

Saved in:

Bibliographic Details
Main Author:	Mingzhu Tang (3923792) (author)
Other Authors:	Wencheng Wang (5978525) (author)
Published:	2025
Subjects:	Cell Biology Genetics Ecology Developmental Biology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> aiming good generalization performance experimental results show composite loss function low recognition accuracy mainstream segmentation models improved network combines final generalization experiment improve segmentation accuracy overfitting problem caused fdtransunet achieves 94 industrial defect segmentation limited defective samples segmentation accuracy defective samples defect samples segmentation model experiment proves defect sample unbalanced foreground net network large number insufficient sample hierarchical structure global self global information feature differentiation effectively extract effectively expanded different scenarios dice coefficient current problems background sizes attention mechanism aluminum based
Tags:	Add Tag No Tags, Be the first to tag this record!

Loss function comparison experiments.

Similar Items