An active learning pipeline with contrastive pretraining and rareness-aware sampling reaches 98% of fully supervised mIoU on semiconductor XRM scans with only about 4.9% of labels.
Au- tomated attribute measurements of buried package fea- tures in 3D X-ray images using deep learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Active Learning for Semiconductor Defect Segmentation
An active learning pipeline with contrastive pretraining and rareness-aware sampling reaches 98% of fully supervised mIoU on semiconductor XRM scans with only about 4.9% of labels.