WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects

Nag, Subhrajit; Makwana, Dhruv; R, Sai Chandra Teja; Mittal, Sparsh; Mohan, C. Krishna

doi:10.1016/j.compind.2022.103720

Cited by 25 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Defect Pattern Recognition (DPR) of wafer maps, Wang et al [18] published the MixedWM38 dataset, additionally designed a Deformable Convolutional Network (DC-Net) and a multi-label output layer for mixed-type defect classification with average accuracy of 93.2%. By testing on the same data, Nag et al [27] presented an encoder-decoder network called WaferSegClassNet (WSCN) for both classification and segmentation tasks. They achieved an average classification accuracy of 98.2% on all 38 classes.…”

Section: A Surface Defect Recognitionmentioning

confidence: 99%

“…Obtained heat-maps indicate that the proposed method precisely gives representative features for the classification task. As showed in Table V, we compare our classification results with DC-Net [18] and WaferSegClassNet (WSCN) [27] in the same setting of using 80% dataset for training the networks and 20% for validation. We obtain the average classification accuracy of 98.22% on all 38 classes, which is superior to DC-Net (93.2%).…”

Section: Experiments On Mixedwm38mentioning

confidence: 99%

See 1 more Smart Citation

Improving Image Representation for Surface Defect Recognition with Small Data

Phuong,

Tin,

Trang

2024

JAIT

View full text Add to dashboard Cite

Automated surface defect detection systems have received much attention for quality control in industrial production. Deep learning techniques are proving their capability in these systems, due to the complexity of defects and inspection requirements. However, in fact, the availability of defective data is a major challenge. It is thus difficult to build an efficient model for a high-accuracy inspection system. In this paper, we present a method to deal with this lack of defective data by using self-contrastive learning to enhance image representations and the margin loss to improve the discriminativeness of defect features. Experiments were performed on the NEU dataset and MixedWWM38 dataset for several data size settings and for the few-shot learning task. The obtained results demonstrate the effectiveness of our proposed method. Particularly, the method achieves an accuracy of 98.83% and 92.27% on NEU dataset and MixedWM38 dataset, respectively, with only 20 training samples per class.

show abstract

Section: A Surface Defect Recognitionmentioning

confidence: 99%

Section: Experiments On Mixedwm38mentioning

confidence: 99%

Improving Image Representation for Surface Defect Recognition with Small Data

Phuong,

Tin,

Trang

2024

JAIT

View full text Add to dashboard Cite

show abstract

“…They have also explored parametrized quantum circuits with several expressibility and entangling abilities. S. Nag et al 6 have proposed a lightweight deep learning model as "WaferSegClassNet" (WSCN) for classification and segmentation of semiconductor wafer defects. To increase the accuracy and decrease model training time, the authors utilized N-pair contrastive loss mechanism.…”

Section: Related Workmentioning

confidence: 99%

Towards improving challenging stochastic defect detection in SEM images based on improved YOLOv5

Dey

Dehaerne²,

Halder

2022

Photomask Technology 2022

View full text Add to dashboard Cite

With the progression of deep learning algorithms in computer vision, a lot of research is taking place in the semiconductor industry towards improving real-time defect detection and classification analysis. An Automated Defect Classification and Detection (ADCD) framework not only enables rapid measurement of dimensions and classification of defects, but also helps minimize production costs, engineering time as well as tool cycle time associated with the defect inspection process. As we continue to shrink the pitch (below 36nm), defect characterization at wafer scale becomes a key issue as it demands rapid measurement but without losing accuracy and repeatability. Also, in the context of high NA lithography (thin resist), accurate metrology becomes difficult with very noisy as well as low contrast images (No BKM exists till now). Human eyes generally demonstrate close to the Bayesian Error limit in detecting smaller objects (for example, extracting contextual information instantaneously from nanoscale defects in SEM images). However, for most One-stage and Two-stage object detectors, this is still a very challenging task due to variable image resolution and SEM (scanning electron microscope) image quality (low SNR). In this research work, we have experimented with different modified YOLOv5 object detectors to improve challenging stochastic defect detection precision. In this work, we have proposed an ensemble strategy by empirically combining multiple custom-trained models (YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) together at the test and inference time. We have noticed four YOLOv5 architecture variants are outperforming against our previous Ensemble ResNets model with improvements of the average precision metric (AP) of the most difficult defect classes as p gap and microbridges as well as overall mAP accuracy. With Ensemble YOLOv5, the p gap AP and microbridge AP metrices have been improved by 35% and 25.33%, respectively, whereas the overall mAP has been improved by 6.25%. The proposed Automated Defect Classification and Detection (ADCD) framework can also be used for high resolution and high-speed metrology, providing rapid identification of defects with improved certainty and further root cause investigation.

show abstract

“…In the integrated circuits manufacturing industry, wafer fabrication is an essential procedure [1][2][3]. The manufacturing process of wafer is divided into two processes: front-end and back-end.…”

Section: Introductionmentioning

confidence: 99%

A class imbalanced wafer defect classification framework based on variational autoencoder generative adversarial network

Wang¹,

Wei²,

Wang³

2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Wafer Defect Classification (WDC) can be crucial to the wafer fabrication process. Engineers can quickly respond to improve the technological process, averting further defects through WDC. However, due to the complex fabrication steps, wafer defects are different in various types. This causes a severe data imbalance problem in WDC. To effectively solve the problem, this study introduces a class imbalanced wafer defect classification framework (CI-WDC) based on Variational Autoencoder Generative Adversarial Network (VAE-GAN). This framework consists of VAE-GAN and wafer defect classifier. Among them, VAE-GAN is responsible for creating new samples to solve the imbalance problem while the classifier is responsible for classifying wafer defect patterns. Specifically, VAE-GAN combines the advantage of a variational autoencoder (VAE) and generative adversarial network. VAE networks can produce subtle differences that do not affect the properties of the data when generating new images. At the same time, the proposed discriminator can help us constrain the generated images to be close to real samples and avoid irrational, feature-missing, and ambiguous samples. WM-811K dataset is utilized to verify the above method. The experimental results validate that the samples generated by VAE-GAN have a significant improvement in the performance of the WDC system.

show abstract

WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects

Cited by 25 publications

References 19 publications

Improving Image Representation for Surface Defect Recognition with Small Data

Improving Image Representation for Surface Defect Recognition with Small Data

Towards improving challenging stochastic defect detection in SEM images based on improved YOLOv5

A class imbalanced wafer defect classification framework based on variational autoencoder generative adversarial network

Contact Info

Product

Resources

About