Self-Supervised Representation Learning for Wafer Bin Map Defect Pattern Classification

Kahng, Hyungu; Kim, Seoung Bum

doi:10.1109/tsm.2020.3038165

Cited by 49 publications

(16 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first trained six networks: ResNet18 23 , AlexNet 24 , and VGG16 25 , DenseNet121 31 , GoogLeNet 32 , and SqueezeNet 33 with the training set. These models are well known and have performed well when adapted to the classification of defected patterns in wafer bin maps 26 – 28 , 34 , 35 . The key salient features of these models are shown in Supplementary file .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A voting-based ensemble feature network for semiconductor wafer defect classification

Misra

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Semiconductor wafer defects severely affect product development. In order to reduce the occurrence of defects, it is necessary to identify why they occur, and it can be inferred by analyzing the patterns of defects. Automatic defect classification (ADC) is used to analyze large amounts of samples. ADC can reduce human resource requirements for defect inspection and improve inspection quality. Although several ADC systems have been developed to identify and classify wafer surfaces, the conventional ML-based ADC methods use numerous image recognition features for defect classification and tend to be costly, inefficient, and time-consuming. Here, an ADC technique based on a deep ensemble feature framework (DEFF) is proposed that classifies different kinds of wafer surface damage automatically. DEFF has an ensemble feature network and the final decision network layer. The feature network learns features using multiple pre-trained convolutional neural network (CNN) models representing wafer defects and the ensemble features are computed by concatenating these features. The decision network layer decides the classification labels using the ensemble features. The classification performance is further enhanced by using a voting-based ensemble learning strategy in combination with the deep ensemble features. We show the efficacy of the proposed strategy using the real-world data from SK Hynix.

show abstract

Section: Resultsmentioning

confidence: 99%

“…These popular CNN models have been widely used in many applications and show their robustness. Many researchers 26 – 28 showed they have achieved the highest classification accuracy using these models for wafer map defect pattern identification. The network architecture of these models is shown in Supplementary Fig.…”

Section: Methodsmentioning

confidence: 99%

A voting-based ensemble feature network for semiconductor wafer defect classification

Misra

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…An experienced inspector can identify the cause of defect depending on the WBM's pattern. The process of manually inspecting these defects is time consuming and may be affected by the fatigue's level of the inspector, especially because modern semiconductors manufacturers produce several thousands of wafers every week [5], [6]. Therefore, many semiconductor manufacturing are investigating this problem using machine learning and computer vision techniques to perform automatic defect detection [3].…”

Section: Introductionmentioning

confidence: 99%

An Improved Capsule Network (WaferCaps) for Wafer Bin Map Classification Based on DCGAN Data Upsampling

Ebayyeh

Daneshvar

Mousavi

2022

IEEE Trans. Semicond. Manufact.

View full text Add to dashboard Cite

Wafer bin maps contain vital information that helps semiconductor manufacturers to identify the root causes and defect pattern failures in wafers. Conventional manual inspection techniques in inspecting these failures are labour intensive and cause prolonged production cycle time. Therefore, automatic inspection techniques can solve this problem. This paper proposes a deep learning approach based on deep convolutional generative adversarial network (DCGAN) and a new Capsule Network (WaferCaps). DCGAN was used to upsample the original dataset and therefore increase the data used for training and balance the classes at the same time. While WaferCaps was proposed to classify the defect patterns according to eight classes. The performance of our proposed DCGAN and WaferCaps was compared with different deep learning models such as the original Capsule Network (CapsNet), CNN, and MLP. In all of our experiment, WM-811K dataset was used for the data upsampling and training. The proposed approach has shown an effective performance in generating new synthetic data and classify them with training accuracy of 99.59%, validation accuracy of 97.53% and test accuracy of 91.4%.

show abstract

“…That is, when a traditional classification algorithm is applied to an imbalance dataset, it often tends to support majority class instances while ignoring minority class instances in order to increase over classification accuracy although the minority class instances are often more informative to the application. Therefore, many useful approaches have been developed to achieve a better class‐instance distribution and to improve the classification performance 18–25 …”

Section: Introductionmentioning

confidence: 99%

“…Therefore, many useful approaches have been developed to achieve a better class-instance distribution and to improve the classification performance. [18][19][20][21][22][23][24][25] Furthermore, it is known that wafer warpage is one of the main root causes leading to a die failure (i.e., defect) in semiconductor manufacturing. 26 As the thickness of the wafer decreases and large stresses are induced during manufacturing processes such as film deposition, CMP, lithography, etch, and various thermal processes, an increasing trend of wafer warpage has been seen.…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid resampling for semiconductor wafer defect bin classification

Park

Pan

Montgomery

2022

Quality & Reliability Eng

View full text Add to dashboard Cite

Generally, defective dies on semiconductor wafer maps tend to form spatial clusters in distinguishable patterns which contain crucial information on specific problems of equipment or process, thus it is highly important to identify and classify diverse defect patterns accurately. However, in practice, there exists a serious class imbalance problem, that is, the number of the defective dies on semiconductor wafer maps is usually much smaller than that of the non-defective dies. In various machine learning applications, a typical classification algorithm is, however, developed under the assumption that the number of instances for each class is nearly balanced. If the conventional classification algorithm is applied to a class imbalanced dataset, it may lead to incorrect classification results and degrade the reliability of the classification algorithm. In this research, we consider the semiconductor wafer defect bin data combined with wafer warpage information and propose a new hybrid resampling algorithm to improve performance of classifiers. From the experimental analysis, we show that the proposed algorithm provides better classification performance compared to other data preprocessing methods regardless of classification models.

show abstract

Self-Supervised Representation Learning for Wafer Bin Map Defect Pattern Classification

Cited by 49 publications

References 25 publications

A voting-based ensemble feature network for semiconductor wafer defect classification

A voting-based ensemble feature network for semiconductor wafer defect classification

An Improved Capsule Network (WaferCaps) for Wafer Bin Map Classification Based on DCGAN Data Upsampling

A novel hybrid resampling for semiconductor wafer defect bin classification

Contact Info

Product

Resources

About