# MM-WAE: Multimodal Wasserstein Autoencoders for Semi-Supervised Wafer Map Defect Recognition

## TL;DR

This paper introduces MM-WAE, a new method for identifying defects in semiconductor wafers using limited labeled data and improving accuracy through multimodal learning.

## Contribution

The novel contribution is a semi-supervised multimodal Wasserstein autoencoder framework for robust wafer defect classification.

## Key findings

- MM-WAE improves classification accuracy and robustness in wafer defect recognition with limited labeled data.
- The method effectively handles class imbalance and complex defect patterns using multimodal feature fusion.
- Experimental results demonstrate significant performance improvements over existing deep learning approaches.

## Abstract

Wafer map defect pattern recognition is a key task for ensuring yield in integrated circuit manufacturing. However, in real production lines it commonly suffers from scarce labeled data, long-tailed class distributions, and limited feature representations, which cause existing deep learning models to degrade in performance, particularly for minority defect classes and complex defect morphologies. To address these challenges, we propose a semi-supervised classification method for wafer maps based on a multimodal Wasserstein autoencoder (MM-WAE). The framework constructs three parallel feature branches in the spatial, frequency, and texture domains, using a multi-head attention mechanism and gating mechanism for adaptive multimodal fusion. This allows defect patterns to be comprehensively characterized by macroscopic geometric distributions, spectral periodic structures, and microscopic texture details. The Wasserstein autoencoder is introduced, with the latent space distribution regularized by a maximum mean discrepancy (MMD) loss using an inverse multiquadratic kernel. Additionally, an inverse class-frequency weighted cross-entropy loss and a modality consistency loss between the encoder and classifier jointly optimize the reconstruction and classification paths while leveraging large amounts of unlabeled wafer maps for semi-supervised learning. Experimental results show that MM-WAE mitigates performance limitations caused by insufficient labels and class imbalance, significantly improving the accuracy and robustness of wafer defect classification, with promising potential for industrial application and further development.