# Iterative Cluster Harvesting for Wafer Map Defect Patterns

arXiv: https://arxiv.org/abs/2404.15436 · HTML: https://mlsanity.com/paper/2404.15436/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 48 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 4 of 4)

- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [CNN features are also great at unsupervised classification](https://mlsanity.com/paper/1707.01700/) (2017)
- [Combining pretrained CNN feature extractors to enhance clustering of complex natural images](https://mlsanity.com/paper/2101.02767/) (2021)

## Built on by (most cited first, 2 of 2)

- [Are Foundation Models Ready for Industrial Defect Recognition? A Reality Check on Real-World Data](https://mlsanity.com/paper/2509.20479/) (2025)
- [Advanced Clustering Framework for Semiconductor Image Analytics Integrating Deep TDA with Self-Supervised and Transfer Learning Techniques](https://mlsanity.com/paper/2505.03848/) (2025)

## Abstract (arXiv)

Unsupervised clustering of wafer map defect patterns is challenging because the appearance of certain defect patterns varies significantly. This includes changing shape, location, density, and rotation of the defect area on the wafer. We present a harvesting approach, which can cluster even challenging defect patterns of wafer maps well. Our approach makes use of a well-known, three-step procedure: feature extraction, dimension reduction, and clustering. The novelty in our approach lies in repeating dimensionality reduction and clustering iteratively while filtering out one cluster per iteration according to its silhouette score. This method leads to an improvement of clustering performance in general and is especially useful for difficult defect patterns. The low computational effort allows for a quick assessment of large datasets and can be used to support manual labeling efforts. We benchmark against related approaches from the literature and show improved results on a real-world industrial dataset.