Active Learning to Reduce Data Requirements For Defect Identification in Semiconductor Manufacturing


A new technical paper titled “Exploring Active Learning for Semiconductor Defect Segmentation” was published by researchers at Agency for Science, Technology and Research (A*STAR) in Singapore.

“We identify two unique challenges when applying AL on semiconductor XRM scans: large domain shift and severe class-imbalance. To address these challenges, we propose to perform contrastive pretraining on the unlabelled data to obtain the initialization weights for each AL cycle, and a rareness-aware acquisition function that favors the selection of samples containing rare classes. We evaluate our method on a semiconductor dataset that is compiled from XRM scans of high bandwidth memory structures composed of logic and memory dies, and demonstrate that our method achieves state-of-the-art performance,” states the paper.

Find the technical paper here. Published October 2022.

L. Cai et al., “Exploring Active Learning for Semiconductor Defect Segmentation,” 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 1796-1800, doi: 10.1109/ICIP46576.2022.9897842.

Related Reading
Why Silent Data Errors Are So Hard To Find
Subtle IC defects in data center CPUs result in computation errors.
Enabling Test Strategies For 2.5D, 3D Stacked ICs
Better standards, 3D DFT, and next-generation probes are a great start toward fully testing these complex systems.
Nanosheet FETs Drive Changes In Metrology And Inspection
Detecting defects inside deep or hidden structures requires a multitool approach.
Making The Most Of Data Lakes
Why data organization and a well-designed data architecture are critical to effectively using manufacturing and design data.

Leave a Reply

(Note: This name will be displayed publicly)