Masked autoencoder self-pretraining applied to microelectronics defect detection
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Applied masked autoencoder self-pretraining to microelectronics defect detection — 9,000 scanning acoustic microscopy (SAM) images of solder joints. Author-measured test MSE was 0.0304 with MAE self-pretraining, better than 0.0335 with ImageNet pretraining and 0.0380 with supervised learning
Why it matters
SAM is the standard non-destructive inspection tool in OSAT (delamination, voids). Evidence, shown directly in a back-end modality, that pretraining on images from one's own domain beats ImageNet. It does not, however, demonstrate label savings
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2504.10021Added in Week 35, 2026 · See that week
On the map — ⑭ Physical World line
- Previous stopNVIDIA releases Cosmos world foundation models
- This record · stopMasked autoencoder self-pretraining applied to microelectronics defect detection
- Next stopGemini Robotics 1.5