Deformable Convolutional Networks for Efficient Mixed-Type Wafer Defect Pattern Recognition
The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Defect pattern recognition (DPR) of wafer maps is critical for determining the root cause of production defects, which can provide insights for the yield improvement in wafer foundries. During wafer fabrication, several types of defects can be coupled together in a piece of wafer, it is called mixed-type defects DPR. To detect mixed-type defects is much more complicated because the combination of defects may vary a lot, from the type of defects, position, angle, number of defects, etc. Deep learning methods have been a good choice for complex pattern recognition problems. In this article, we propose a deformable convolutional network (DC-Net) for mixed-type DPR (MDPR) in which several types of defects are coupled together in a piece of wafer. A deformable convolutional unit is designed to selectively sample from mixed defects, then extract high-quality features from wafer maps. A multi-label output layer is improved with a one-hot encoding mechanism, which decomposes extract mixed features into each basic single defect. The experiment results indicate that the proposed DC-Net model outperforms conventional models and other deep learning models. Further results of the interpretable analysis reveal that the proposed DC-Net can accurately pinpoint the defects areas of wafer maps with noise points, which is beneficial for mixed-type DPR problems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 1×
“Among the machine learning technologies, the deformable convolutional (DC) network [27] selectively samples from input data based on the position information for further displacement adjustment, which has been extensively applied in multi-angle object detection and hyperspectral image classification…”
BackgroundA new convolutional neural network-based data-driven fault diagnosis method
Wen, L., Li, X., Gao, L., & Zhang, Y. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2774777 · Cited by 2,222 · cited 1×
“With the development of artificial intelligence, deep learning methods extract features from raw data automatically through multi-layer neural networks [21]–[23], which shows incredible performance in computer version tasks [24].”
MethodSelf-citationEdvr: video restoration with enhanced deformable convolutional networks
Wang, X., Chan, K. C. K., Yu, K., Dong, C., & Loy, C. C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00247 · Cited by 1,272 · cited 1×
“Wang et al. [31] devised a DC neural network module to align different frames at the feature level to handle large motions in video restoration tasks.”
BackgroundLee, K. B., Cheon, S., & Kim, C. O. (2017) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2017.2676245 · Cited by 483 · cited 1×
“After the wafer manufacturing, wafer test is conducted to evaluate the electrical function of each die by probe test [2], which consists of many test items that measure the performance of the operations of required die electronic functions.”
MethodWafer Map Defect Pattern Classification and Image Retrieval Using Convolutional Neural Network
Nakazawa, T., & Kulkarni, D. V. (2018) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2018.2795466 · Cited by 408 · cited 3×
“The performances of the proposed DC-Net were first compared with Takeshi_CNN [25], Kiryong_CNN [26].”
BackgroundMethodWafer Map Failure Pattern Recognition and Similarity Ranking for Large-Scale Data Sets
Wu, M.-J., Jang, J.-S. R., & Chen, J.-L. (2015) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2014.2364237 · Cited by 400 · cited 2×
“Aiming to achieve high accuracy, shallow models should be equipped with good feature extractors (such as correlogram and Radon transform [18]), which can obtain differentiable features from raw data.”
BackgroundA brief introduction to OpenCV
Čuljak, I., Abram, D., Pribanić, T., Džapo, H., & Cifrek, M. (2012) · International Convention on Information and Communication Technology, Electronics and Microelectronics · Cited by 376
AI-based modeling and data-driven evaluation for smart manufacturing processes
Ghahramani, M., Qiao, Y., Zhou, M. C., O'Hagan, A., & Sweeney, J. (2020) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003114 · Cited by 334 · cited 1×
“With the development of artificial intelligence, deep learning methods extract features from raw data automatically through multi-layer neural networks [21]–[23], which shows incredible performance in computer version tasks [24].”
MethodDeformable Convolutional Neural Networks for Hyperspectral Image Classification
Zhu, J., Fang, L., & Ghamisi, P. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2830403 · Cited by 244 · cited 1×
“…the machine learning technologies, the deformable convolutional (DC) network [27] selectively samples from input data based on the position information for further displacement adjustment, which has been extensively applied in multi-angle object detection and hyperspectral image classification [28].”
BackgroundClassification of Mixed-Type Defect Patterns in Wafer Bin Maps Using Convolutional Neural Networks
Kyeong, K., & Kim, H. (2018) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2018.2841416 · Cited by 228 · cited 9×
“In Kyeong and Kim’s work [26], 16 defects mixed with”
BackgroundMethodInfluential
Cited by
Items 101–200 of 232
Sequential wafer map inspection via feedback loop with reinforcement learning
Dekhovich, A., Soloviev, O., & Verhaegen, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126996 · Cited by 7
A Fast Postprocessing Algorithm for the Overlapping Problem in Wafer Map Detection
Li, Y., & Jian-guo, W. (2021) · Journal of Sensors · doi:10.1155/2021/2682286 · Cited by 5
“Experiments on the 6 category wafer map datasets [28] used 2 k training images and 382 validation sets and 429 test images.”
BackgroundMethodTripletMatch: Wafer Map Defect Detection Using Semi-Supervised Learning and Triplet Loss With Mixup
Lim, C., & Hur, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3510681 · Cited by 5
Memristive CNN for Wafer defect detection
Chithra, R., Aswani, A. R., & James, A. P. (2022) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas48785.2022.9937406 · Cited by 5
“Software level wafer defect classification problems are addressed in the literature using various machine learning and deep learning algorithms like Convolutional neural network (CNN) [1], [3], autoencoders, Gener-ative Adversarial Networks [4] etc.”
BackgroundSmall Photoresist Defect Samples Augmentation Based on Generative Adversarial Network
Yang, G., Li, Z., Yang, Z., & Cui, S. (2023) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec56291.2023.10082214 · Cited by 5
“Many defects [5] can occur due to changes in the nature of the photoresist or impurities.”
BackgroundSelf-citationResearch on Ship-Engine-Room-Equipment Detection Based on Deep Learning
Chen, R., Zhang, J., & Shen, H. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12040643 · Cited by 5
Self-citationCi, J., Tan, H., Zhai, H., & Tang, X. (2024) · Remote Sensing · doi:10.3390/rs16162953 · Cited by 4
“Li et al. [16] proposed an improved algorithm based on YOLOv4; Wang et al. [17] proposed a deformable convolutional network (DCNet) for hybrid defect pattern recognition; Zhao et al. [18] raised a fast R-CNN algorithm with deformable convolution for recognizing small targets and used it for steel…”
MethodMixed-defect wafer map separation and detection based on single-defect wafer map
Li, J., Long, K., Chen, R., Li, Y., & Huang, X. (2025) · Computers & Industrial Engineering · doi:10.1016/j.cie.2025.111395 · Cited by 4
Zhang, X., Liang, X., Li, J., & Wei, S. (2025) · Computers in Industry · doi:10.1016/j.compind.2025.104391 · Cited by 4
Zhou, W., Wang, G., & Li, Y. (2025) · Integration · doi:10.1016/j.vlsi.2025.102595 · Cited by 4
Liao, X., Zhang, J., Lyu, Y., & Wang, J. (2026) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.12.026 · Cited by 5
Self-citationImproving Image Representation for Surface Defect Recognition with Small Data
Phuong, T. T., Tin, D. D., & Trang, L. H. (2024) · Journal of Advances in Information Technology · doi:10.12720/jait.15.5.572-579 · Cited by 5
“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.”
MethodInfluentialDai, M., Liu, Z., & He, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad730b · Cited by 4
Façoco, I. S., Carvalho, R., & Rosado, L. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200576 · Cited by 6
Gu, S., Lei, Z., Wen, G., Xu, Q., Li, Z. S., Chen, X., & Yang, C. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113962 · Cited by 9
Zhao, W., Liu, Y., Gu, Y. A., & Shi, X. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02713-2 · Cited by 4
Lightweight Hybrid Wafer Defect Pattern Network Based on Feedforward Efficient Attention
Hu, Z., & Wu, Y. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70075 · Cited by 5
Ni, T., Wen, J., Liang, H., Wen, X., & Nie, M. (2026) · Computers in Industry · doi:10.1016/j.compind.2025.104432 · Cited by 4
Review of wafer defect detection in semiconductor manufacturing: Algorithms, systems, and data
Li, J., Zhang, X., Liang, X., Yin, G., Yan, L., & Wei, S. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02845-z · Cited by 4
WGrid: Wafermap Grid Pattern Recognition with Machine Learning Techniques
Liao, P. Y.-Y., Li, K. S.-M., Chen, L. L.-Y., Wang, S.-J., Huang, A. Y.-A., Cheng, K. C.-C., Tsai, N. C.-Y., & Chou, L. (2021) · IEEE International Test Conference (ITC) · doi:10.1109/itc50571.2021.00043 · Cited by 3
Zhao, J., & Tang, L. (2023) · China Semiconductor Technology International Conference (CSTIC) · doi:10.1109/cstic58779.2023.10219303 · Cited by 4
Simultaneous classification and out-of-distribution detection for wafer bin maps
Choi, J., Ma, E.-Y., & Kim, H. (2023) · Quality Engineering · doi:10.1080/08982112.2023.2286497 · Cited by 4
“Wang et al. (2020) proposed the use of a deformable CNN for improved classification of mixed-type defect patterns by leveraging deformable convolutions with selective sampling in place of fixed convolutions.”
Ma, C., Yao, Y., Jie, L., & Hu, L. (2023) · International Workshop on Advanced Patterning Solutions (IWAPS) · doi:10.1109/iwaps60466.2023.10366060 · Cited by 4
“MixedWM38 is a publicly available dataset introduced by Wang et al. [15], specifically designed for inspecting defect patterns on wafer surfaces.”
COFA: counterfactual attention framework for trustworthy wafer map failure classification
Feng, K., Wang, J., Yin, C., & Li, A. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06488-0 · Cited by 4
“We conduct the experiments on the WM-811K dataset [44] and the MixedWM38 [45] dataset.”
Self-citationEvaluating the performance of 6T SRAM cells by deep learning
Khorrami, P., & Nabavi, A. (2024) · Microelectronics Reliability · doi:10.1016/j.microrel.2024.115374 · Cited by 4
Survey of semiconductor wafer defect detection method based on machine vision
Hu, Z., & Wu, Y. (2025) · Journal of Image and Graphics · doi:10.11834/jig.240053 · Cited by 3
Peng, D., Wang, Y., Zhou, X., Liu, J., Liu, C., & Han, T. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3560087 · Cited by 3
“Wang et al. [5] have introduced a wafer defect dataset of mixed types and leveraged deformable convolution to selectively extract pertinent information from the input data, thereby addressing the complexity and heterogeneity inherent in the dataset.”
InfluentialWafer Defect Image Generation Method Based on Improved Styleganv3 Network
Zou, J., Wang, H., & Zhong, J. (2025) · Micromachines · doi:10.3390/mi16080844 · Cited by 3
DG-ViT: a density-guided dual-stream vision transformer for wafer defect detection
Xu, R., Xu, Z., Wang, J., Shen, J., Wen, L., Xie, Y., & Yang, Y. J. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae234a · Cited by 3
“In recent years, several prominent CNN models have been developed, including AC-LDN [5], R-CNN [1], and DHCNN [22].”
Self-citationAn Efficient Detection Method for Wafer-Test-Induced Defects
Wang, Z., Chen, G., Sun, W., Wu, X., Zheng, L., Zhang, Y., & Liu, Q. (2025) · Electronics · doi:10.3390/electronics14234664 · Cited by 3
A deep active learning framework for defect classification of wafer bin maps under noisy labels
Lim, C., Kim, G., & Lim, S. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104621 · Cited by 3
BSCGAN: structured minority class image generation under class-balanced pretraining
Wan, Q., Zhou, B., & Wang, Y. (2024) · The Visual Computer · doi:10.1007/s00371-024-03635-5 · Cited by 3
“The performance of the BSCGAN model is evaluated using four image datasets, including the Fashion-MNIST [39], CIFAR-10 [40], BreakHis breast cancer tissue dataset [41] and WAFER defect map dataset [42].”
DFUNET: A Residual Network for Retinal Vessel
Wu, C., Cheng, Y., Li, W., Yang, Z., & Lu, Z. (2021) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse51940.2021.9569294 · Cited by 3
Self-citationWafer Map Defect Recognition and Accurate Localization Based on Defect Completion Algorithm
Sang, T., Sun, D., Zhao, W. T., Chen, R., & Zeng, Z. (2023) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram55796.2023.10370761 · Cited by 3
“The proposed solution in [20] for mixed-type defect pattern recognition (MDPR) is a deformable convolutional network (DC-Net), which is specifically designed to handle the challenge of detecting multiple defect types on a single wafer.”
LDF-BNN: A Real-Time and High-Accuracy Binary Neural Network Accelerator Based on the Improved BNext
Wan, R., Cen, R., Zhang, D., & Wang, D. (2024) · Micromachines · doi:10.3390/mi15101265 · Cited by 5
“Our design also maintains a high accuracy of 98.70% on the Mixed WM-38 dataset [12], which can demonstrate the potential of LDF-BNN in the field of defect detection.”
MethodInfluentialAn Elegantly Simple Approach for Wafer Feature Extraction and Defect Pattern Recognition
Shukla, N. (2023) · CAS proceedings · doi:10.1109/cas59036.2023.10303648 · Cited by 4
“We conduct our experiments on the MixedWM38[15] dataset which contains 7015 wafer images consisting of the defects described above.”
BackgroundMethodA Selective Convolution Kernel Residual Network for Wafer Map Defect Pattern Recognition
Xu, Y., Lei, Z., Gu, S., Feng, R., Su, Y., & Wen, G. (2024) · Global Reliability and Prognostics and Health Management Conference (PHM) · doi:10.1109/phm-beijing63284.2024.10874517 · Cited by 2
“Mixed-WM38 was collected by Wang [4] in a real wafer fabrication plant.”
State-space models and depth separable convolution for high-precision hybrid wafer defect detection
Zhang, H., Lang, T., Wang, C., Liu, W., Tang, S., & Ji, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07521-2 · Cited by 2
A Wafer Defect Detection Method for Unbalanced Data
Shi, T., Wang, X., & Mao, J. (2025) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-025-02227-2 · Cited by 3
“…that extends the stochastic generalized regression network model for identifying and classifying single and hybrid defect patterns on wafers, and Wang et al. [14] proposed a deformable convolutional network (DC-Net), and used a unique thermal coding mechanism for hybrid wafer defect classification.”
Liu, J., & Wang, H. (2025) · ISA Transactions · doi:10.1016/j.isatra.2025.09.005 · Cited by 2
Adaptive Transfer Learning With Deformable Convolution for Wafer Defect Pattern Recognition
Chou, J., Wang, F., & Chen, H.-K. (2025) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2025.3610478 · Cited by 5
“In 2020, Wang et al. [12] real-world fabrication.”
InfluentialMixed-type wafer defect recognition using optimized YOLOv8 model
Tee, Y. R., Khairuddin, A. S. M., Shah, N. M., & Al-Juboori, H. M. (2026) · Physica Scripta · doi:10.1088/1402-4896/ae4181 · Cited by 2
Dekhovich, A., & Soloviev, O. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00149 · Cited by 4
“Open databases such as WM-811k [42] and MixedWM38 [38] facilitate the development of deep learning algorithms because accessing real-world wafers is expensive and can be associated with data privacy issues.”
Shi, R., Liu, R., Zhou, Z., & Zhou, X. (2026) · Electronics · doi:10.3390/electronics15071437 · Cited by 2
Zhao, L., Chang, J., & Yu, J. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02880-w · Cited by 2
Hybrid Deep Learning Pipeline for Advanced Electrical Wafer Defect Maps Assessment
Rundo, F., Coffa, S., Calabretta, M., Sarpietro, R. E., Messina, A. A., Pino, C., Palazzo, S., & Spampinato, C. (2022) · AEIT International Annual Conference · doi:10.23919/aeit56783.2022.9951783 · Cited by 2
An end-to-end wafer map defect recognition model
Xia, M., Mu, X., & Wu, Z. (2024) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea62105.2024.10603564 · Cited by 2
Rundo, F., Calabretta, M., Rundo, M., Castagnolo, G., Pino, C., Battiato, S., & Messina, A. A. (2024) · IEEE International Workshop on Metrology for Automotive (MetroAutomotive) · doi:10.1109/metroautomotive61329.2024.10615739 · Cited by 2
“…a VGG-based architecture trained on denoised Wafer Maps, processed through a Hough transform-based method, achieving an accuracy of 98.70 In [13], a hybrid model was introduced, incorporating data augmentation for various mixed failure patterns, followed by a CNN trained on 38 different…”
MethodInfluentialPaLM: Point Cloud and Large Pre-trained Model Catch Mixed-type Wafer Defect Pattern Recognition
He, H., Kuang, G., Sun, Q. L., & Geng, H. (2024) · Design, Automation, and Test in Europe · doi:10.23919/date58400.2024.10546714 · Cited by 2
“Despite the importance of recognizing mixed-type wafer defect patterns, few works [4], [5] exploiting CNN and transformer architectures have been proposed to address the dilemma.”
BackgroundMethodInfluentialSegmentation-Enhanced Overlapped Defect Identification for Multipatterns Wafer Maps
Ni, T., Jiang, W., Liang, H., Wen, X., & Nie, M. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3565049 · Cited by 2
“Wang et al. [20] used deformable convolutional networks (DC-Net) for multipattern defect detection and construct a public dataset MixedWM38, which includes a large number of multipattern and overlapped defects.”
InfluentialImproving wafer map classification in Industry 4.0
Scheiber, M., Nartey, C., Zernig, A., & Kaestner, A. (2022) · IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) · doi:10.1109/icps51978.2022.9816887 · Cited by 2
Pre-trained CNN-based TransUNet Model for Mixed-Type Defects in Wafer Maps
Kim, Y., Lee, J.-H., & Jeong, J. (2023) · WSEAS Transactions on Information Science and Applications archive · doi:10.37394/23209.2023.20.27 · Cited by 2
Zhao, S., Zhang, G., Liu, S., Zhang, J., Bandara, H. M. N. D., Zhong, R. Y., & Wang, L. (2025) · Engineering · doi:10.1016/j.eng.2025.08.023 · Cited by 3
Self-citationTAB: Text-Align Anomaly Backbone Model for Industrial Inspection Tasks
Lee, H.-W., & Lai, S. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00396 · Cited by 2
“We have validated our approach on four benchmark datasets: MVTecAD[2], BTAD[12], KSDD2[3], and MixedWM38[18].”
MethodChen, J., Zhao, Y., & Wang, H. (2025) · Journal of Electrical and Computer Engineering · doi:10.1155/jece/2935790 · Cited by 1
Efficient Modulated State Space Model for Mixed-Type Wafer Defect Pattern Recognition
Nie, M., Zhu, S., Yan, A., Cheng, Z., Wen, X., & Ni, T. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10992855 · Cited by 1
“This surge in data has driven significant advancements in defect recognition algorithms, particularly those based on deep learning techniques [1], [3].”
Mirani, I. K., Yu, N., & Khan, M. A. A. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090876 · Cited by 1
Pan, Y., Sun, Y., Qin, W., Gao, Z., & Liu, L. (2026) · Control Engineering Practice · doi:10.1016/j.conengprac.2026.106759 · Cited by 1
Fan, S. S., & Huang, Y. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3692570 · Cited by 1
“To further validate the proposed approach, the MixedWM38 dataset [41] was revisited to evaluate the performance of the new SCAN model.”
Graph-based contrastive learning for self-supervised semiconductor wafer defect detection
Awais, M., Postolache, O. A., & Oliveira, S. M. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02906-3 · Cited by 1
Yang, D., Jang, J., & Kim, C. O. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130127 · Cited by 1
Wafer Defect Recognition for Industrial Inspection: FCS-VMamba Model and Experimental Validation
Zhang, Y., Ma, Z., Cui, T., Zhao, T., Wang, Q., & Wang, J. (2026) · Journal of Imaging · doi:10.3390/jimaging12040142 · Cited by 1
“Wang et al. [22] proposed deformable convolutional networks (DC-Nets) that adaptively sample mixed defect regions, significantly improving mixed defect recognition.”
Self-citationHasan, M. M., Yu, N., & Mirani, I. K. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11521936 · Cited by 1
“The publicly available WM-811K [10] dataset exhibits significant class imbalance, while the MixedWM38 [11] dataset contains composite defect patterns.”
Deep Learning for Automatic Wafer Monitoring System
Rundo, F., Calabretta, M., Pino, C., Coffa, S., Messina, A. A., Spampinato, C., & Battiato, S. (2023) · Smart Systems Integration Conference and Exhibition (SSI) · doi:10.1109/ssi58917.2023.10387766 · Cited by 2
“MixedWM38 dataset [20].”
Islam, M. M. M. (2025) · Springer series in advanced manufacturing · doi:10.1007/978-3-031-80154-9_7 · Cited by 1
Kim, T., & Behdinan, K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4605931 · Cited by 2
Data Generation with Structure Enforcing Adversarial Learning
Solomon, I., Kumar, U., & Senthilnath, J. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222210
“The wafer defect map dataset [19] is collected from the wafer manufacturing plant and it contains 38000 mixed mode wafer map defect data.”
MethodUnsupervised Wafer Defect Classification Model Based On Joint Reconstruction And Clustering
Jie, L., Guo, Y., Yao, Y., & Liu, Y. (2023) · Advances in Engineering Technology Research · doi:10.56028/aetr.9.1.182.2024
Classification of Chip-Level Defect Types in Wafer Bin Maps Using Only Wafer-Level Labels
Lee, H., Kim, H., & Kim, H. (2024) · Journal of Manufacturing Science and Engineering · doi:10.1115/1.4065226
zhao, W., Liu, Y. K., Yan, R. X., Gao, Y., & Gu, Y. A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4902014 · Cited by 1
Integrated Enhanced Feature Fusion Module For Photovoltaic Defect Detection Network
Zhou, Y., Xu, S., Chen, H., & Liu, K. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662155
U-Tell: Unsupervised Task Expert Lifelong Learning
Solomon, I., Aung, A. P. P., Kumar, U., & Senthilnath, J. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647977 · Cited by 4
zhao, W., Gu, Y. A., Liu, Y. K., Yan, R., & Gao, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5084918
DCUE-YOLO: A Lightweight Model in Industrial Defect DetectionPreprint
Zhong, J., Wang, H., & Zou, J. (2025) · Research Square · doi:10.21203/rs.3.rs-5790775/v1
Yang, G., Yang, Z., Pan, J., Miao, Y., & Cui, S. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3529557
“Concurrently, Wang et al. [10] introduce a versatile convolutional network, known as dc-Net, which is specifically engineered for the recognition of mixed-type defect patterns (MDPR).”
Self-citationA Feature Pyramid Residual Network with Attention Mechanism for Wafer Map Mixed Defect Detection
Zhao, D., Lei, Z., Feng, R., Gu, S., Su, Y., & Wen, G. (2024) · Global Reliability and Prognostics and Health Management Conference (PHM) · doi:10.1109/phm-beijing63284.2024.10874728 · Cited by 1
Gu, S., Lei, Z., Zhao, D., Feng, R., Su, Y., & Wen, G. (2024) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd64214.2024.10920561
“Wang et al. [6] used deformable convolution to adaptively capture defects of different shapes and classified 38 types of defects (including 29 mixed-type defects).”
Recognition and ranking using similarity on defective wafer bin maps
Kwon, Y. P., Oh, S., & Kim, H. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-15685-7
“We evaluated the proposed search algorithms on industry-driven WM-811K [20] and MixedWM38 [41] datasets.”
TSMDM-Net: A Speech Emotion Recognition Model Based on Multi-scale Time Series Dynamic Modeling
Wei, W., Wang, Y., Zhang, B., & Duan, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0009-3_14
Zhong, J., Wang, H., & Zou, J. (2025) · Journal of Intelligent & Fuzzy Systems · doi:10.1177/18758967251369774
“To assess the effectiveness of our proposed approach, evaluate our method using three datasets: the PCB board dataset (Beijing University, 2024), the NEU-DET steel dataset (Northeast University, 2024), and the mixed-type WM38 dataset (Wang et al., 2020).”
Gu, S., Wen, G., Lei, Z., Feng, R., Zhao, D., & Xu, Y. (2025) · International Conference on Equipment Intelligent Operation and Maintenance (ICEIOM) · doi:10.1109/iceiom65271.2025.11239907
“The experiments are conducted on the Mixed-WM38 dataset collected from a real-world wafer manufacturing facility [15].”
Multi-Scale Content-Aware Enhancement Dual-Branch CNN for LED-Chip Defect Classification
Wei, L., & Cai, J. (2025) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2025.3642343
“Recently, surface defect detection using neural networks has attracted a lot of attention in industrial fields [5], [6], [7], because neural networks can implement an end-to-end automatic detection system and allow laborers to be released.”
A Novel Deep-Broad Learning Network for Mixed Wafer Map Defect Recognition
Zhou, Q., Song, M., & Yang, L. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11150303
“(3) where, a stage typically refers to a series of cascaded structures, such as the convolutional and pooling layers in a VGG network, residual blocks in a ResNet, or Efficient Blocks in an EfficientNet [15].”
Transductive zero-shot learning for mixed-type defect classification in wafer maps
Liu, J., Lu, J., Chen, T., Wu, X., Liang, H., Yuan, X., & Pham, Y. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02775-2
Banba, H., & Ichiro, O. (2026) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ae3323
Kakarla, D. (2025) · i-manager’s Journal on Electronics Engineering · doi:10.26634/jele.16.1.22349
Liu, B., Tian, Y., Chai, S., Zhang, Z., & Zeng, Z. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343177
“Fig.1 shows the defect detection process, together with eight types of defect patterns in the public WM-811K dataset [6].”
Liao, X., Zhang, J., Wang, J., Lyu, Y., Zhong, R. Y., & Zhang, Q. (2026) · International Journal of Production Research · doi:10.1080/00207543.2026.2623534
“For instance, Wang et al. proposed a deformable convolutions network that extract spatially adaptive features from wafer defects (Wang et al. 2020).”
Self-citationElectrical Wafer Sorting: a Deep Learning Approach for Advanced Wafer Defect Map Evaluation
Fiore, M., Sitta, A., Sequenzia, G., Rundo, F., & Calabretta, M. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-3-032-14950-3_15
Mixed-Type Wafer Map Defect Classification Using Regional-to-Local Attention
Akhter, S., Raiyan, T. M., Hossain, M. Z., Shadman, T. M., & Hossain, M. I. (2025) · International Conference on Sustainable Technologies for Industry 5.0 (STI) · doi:10.1109/sti69347.2025.11367500
Jain, S., Kumari, A. C., & Srinivas, K. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02797-4
Toward wafer defect detection: An incremental industrial large model with prompt-aware memory replay
Yue, K., Li, J., Deng, S., Chen, Z., Kwoh, C. K., & Li, W. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114815
Binary and Multiclass Classification for Wafer Defects Using ResNet
Divya Vani, G., Chinnaiah, M. C., Basha, M., Vannala, V., Teja, T. S., & Nikhil, V. (2025) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon67554.2025.11379858
“The system shows real-time defect detection on silicon wafers using BNN various processing techniques to enable efficient defect classification mechanisms on Mixed-type Wafer Defect Dataset [1].”
Adaptive open-world learning for analyzing wafer map variations
Wu, Y., Shen, L., Yan, H., Liu, X., & Xu, C. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131994
Self-citationChoi, J., & Kim, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-10356216/v1
Dynamic Meta-Learning with Attentional Prototypes for Few-Shot Wafer Defect Recognition
Ni, T., Yu, M., Chen, X., Liang, H., Wang, S., Cheng, M., & Nie, M. (2026) · Journal of Electronic Testing · doi:10.1007/s10836-026-06224-7
“The MixedWM38 dataset is a curated subset derived from the WM-811K dataset and was constructed by Wang et al. [4].”
Dang, J.-F., & Wu, C.-C. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001426500230
Kawale, A., Nachanekar, M., & Rangari, F. (2026) · Contemporary Computing Innovations Conference (CCIC) · doi:10.1109/ccic68129.2026.11486004
“Hence, quality wafer defect inspection has become key to semiconductor manufacturing reliability in production [1-3].”
Vision Transformer-Based Framework for Reliable Semiconductor Wafer Defect Classification
Musha, A., Turjo, C. M., & Ghosh, T. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491308
“In modern semiconductor wafer manufacturing systems, defect pattern recognition on WMs is often performed manually by skilled engineers, which is both labor-intensive and costly [2].”
A hybrid attention-based fusion network for mixed wafer map defect recognition
Zhou, Q., Ma, M. M., Liu, Y., & Lei, Y. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05385-4
“Wang et al. [6] introduced DC-Net, a deformable convolution-based hybrid wafer defect recognition network, which used deformable convolution units for selective image sampling and a more balanced dataset for enhanced performance.”
Metadata
- Authors
- Wang, J., Xu, C., Yang, Z., Zhang, J., & Li, X.
- Affiliations
- Donghua University (CN)
- Shanghai Jiao Tong University (CN)
- Centro de Investigación y de Estudios Avanzados del Instituto Politécnico Nacional (MX)
- Venue
- IEEE Transactions on Semiconductor Manufacturing
- Published
- 2020-11
- Volume
- 33
- Issue
- 4
- Pages
- 587-596
- ISSN
- 0894-6507 (ISSN-L)
- 1558-2345
- OpenAlex
- W3082906739
- Cited by
- 229
- References
- 34
- Citations by year
- 2026: 53 · 2025: 52 · 2024: 42 · 2023: 38 · 2022: 20 · 2021: 22 · 2020: 2
- FWCI
- 13.07
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Semiconductor Manufacturing (publishedVersion)
- Funders
- National Natural Science Foundation of China (51905091)
- Fundamental Research funds for the Central Universities (2232019D3-34)
- Shanghai Sailing Program (19YF1401500)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- deformable convolutional networks, wafer maps, multi-label classification, one-hot encoding, defect root cause analysis, explainable deep learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.