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 201–232 of 232
An image-based damage detection system for sealing surfaces of nuclear power valves
Wang, X. J., Cao, S., Sun, T., & Gao, H. (2026) · Energy · doi:10.1016/j.energy.2026.141281
Mahmoudpour, S., Sake, B., Velasco, D. A., Sung, M., Choi, J.-K., Schelkens, P., & Kim, H. (2026) · Applied Optics · doi:10.1364/ao.599473
Liu, J., Lou, Y., Wu, B., Qiao, Y., Hong, J., Huang, G., & Tu, D. (2026) · Materials & Design · doi:10.1016/j.matdes.2026.116356
Wafer map pattern recognition using ternary spiking neural networks
Mishra, A. K., Das, A. K., & Kandasamy, N. (2026) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2026.105299
Wafer Defect Classification Based on Peak-Enhanced Multidomain Fusion Network
Hao, S., Duan, J., Wang, H., Zeng, Y., & Yu, J. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3704389
“The experiments were conducted on two widely used wafer defect datasets, WM-811K [31] and MixedWM38 [32].”
Xiao, F., Song, Y., & Chen, J. (2026) · International Conference on Electronics, Circuits and Information Engineering (ECIE) · doi:10.1109/ecie69549.2026.11565751
“During the wafer test process, the electrical performance of each die is assessed through test probes, and the spatial distribution of defective dies forms characteristic patterns on the wafer map that directly reflect specific process anomalies [2].”
Speeding up chip-yield analysis by improved quantum Bayesian inference
Li, Z.-M., Li, Z., Li, T., & Liu, Y.-X. (2026) · Physical Review Applied · doi:10.1103/bk33-qzls
FAD‐Net: An Efficient Architecture for Defect Recognition in Semiconductor Wafers
Mirani, I. K., Yu, N., & Khan, M. A. A. (2026) · Quality and Reliability Engineering International · doi:10.1002/qre.70321
Review of Neural Networks in Wafer Defect Detection: Techniques, Applications, and Challenges
Hou, Z., Xu, Y., Zhang, X., Li, J., Jiang, Y., & Su, H. (2026) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac70275.2026.11585156
A spatial-frequency information fusion network for mixed wafer defect recognition
Zhou, Q., Li, Y., Liu, Y., & Yang, L. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2699953
A Review on the Application of Deep Learning in Wafer Defect Detection
Li, M., Su, H., Shi, C., Zhang, Y., Cheng, X., & Xie, Y. (2026) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac70275.2026.11585140
“…equipment; local defects form local clusters, indicating particle contamination; near-full defects manifest as widespread defects covering most of the wafer; scratch defects are linear tracks caused by improper processing; random defects are randomly distributed on the wafer surface [11].”
A Method for High-Precision Detection of Wafer Surface Tiny Scratches Based on Improved YOLO
Jiang, D., Li, S., Gao, M., Cui, R., Zhang, X., & Wan, Z. (2026) · International Conference on Electronic Engineering and Information Systems (EEISS) · doi:10.1109/eeiss69782.2026.11584539
“Wang et al. [9], for example, created a deformable convolution to fix problems with shapes that are different from each other.”
Efficient knowledge distillation with emphasized Radon features for wafer bin map classification
Ryoo, S., Kim, J., Cho, J., Lee, J. I., Hong, J., & Han, S. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115299
Prakash, S. S., Sahoo, J. P., Wang, T., & Mondal, S. K. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2014-4_38
Du, X., & Dong, M. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05557-2
“We evaluated our method on the MixedWM38 dataset [27], which contains 38,015 wafer images (resized to 52 × 52) covering 1 normal class, 8 single-defect types, and 29 mixed-defect combinations.”
Generation of Constrained Combinatorial Tests for Multi-Label Classifiers
Teruya, K., Tsuchiya, T., Bombarda, A., & Gargantini, A. (2026) · IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) · doi:10.1109/icstw72326.2026.00043
Jiang, D., Li, S., & Sun, Y. (2026) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2026.3714028
“To further advance detection capabilities, Wang et al. [14] introduced deformable convolutions to address the challenges posed by irregularly shaped defects.”
Islam, M. M. M., & Prasad, G. (2026) · Scientific Reports · doi:10.1038/s41598-026-63373-7
“The proposed approach is evaluated on the MixedWM38 benchmark dataset, which comprises 38015 WDMs spanning a diverse set of defect classes commonly observed in semiconductor manufacturing 16 .”
Parameter-Efficient Adaptation of Visual Foundation Model for Wafer Map Defect Classification
Bejani, M., Mauri, M., & Mariani, S. (2026) · IEEE Access · doi:10.1109/access.2026.3722981
“MixedWM38 [40], in turn, contains 38,015 wafer maps with binary multi-label annotations across 8 base defect types, enabling evaluation of co-occurring overlapping defect patterns.”
Islam, M. Z., Sorker, M. S., Antor, J. H., Ahammed, N., & Mamun, M. F. A. (2026) · International Siberian workshops and tutorials on electron devices and materials · doi:10.1109/edm69524.2026.11632237
“The MixedWM38 dataset [1] serves as the primary benchmark, consisting of over 38,000 wafer maps at a 52 × 52 spatial resolution.”
hu, Q. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7291464
DiffWaferNet: a lightweight differential attention-based network for wafermap defect classification
Uddin, M. R., Islam, M. S., Farid, F. A., Uddin, J., & Mansor, S. B. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3947
Wavelet attention fusion network for wafer defect recognition with noise interference
Zhang, F., Zehua, D., & Wang, Y. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae9ded
“Wang et al [24] employed a deformable convolutional network for the classification of 38 hybrid defects.”
Kiran, G. U., Srilakshmi, V., VeeraSekharReddy, B., Mounika, M., SaiLikhitha, B., & Vaishnavi, G. (2026) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc70182.2026.11686917
Anisotropic Hyper-Grid Coresets for Resource-Constrained Retraining of Visual Defect Classifiers
Calvagna, A., Caruso, A. O., Rundo, F., Battiato, S., & Tramontana, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39028-8_25
Shen, J., hu, Q., & Wang, J. (2026) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc66907.2026.11694684
Self-citationZhang, Y.-L., Chen, S.-L., Zhang, H.-T., Feng, M.-W., Dong, Z. S., Lin, J.-X., & Zou, N.-M. (2026) · International Test Conference in Asia · doi:10.1109/itc-asia71864.2026.11710855
“CNN methods, such as DCNet [5] and segmentation-based methods [8], improve recognition performance by extracting hierarchical local features or incorporating defect region information.”
Wafer Map Defect Pattern Recognition via Hierarchical Slimmable Network
Le, T. D., Dinh, T. N., Choi, J., Ahn, J. S., Mondal, S., Doan, V. H. M., & Oh, J. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3742081
“To assess generalization beyond WM-811K, we additionally evaluate on the MixedWM-38 dataset [39], using its single-pattern subset: the eight single-defect classes matching our taxonomy (Center, Donut, Edge-Loc, Edge-Ring, Loc, Near-Full, Random, and Scratch) and the defect-free class, partitioned…”
Kang, S.-H., Kim, W., Chegal, W., & Lee, S. (2026) · IEEE Access · doi:10.1109/access.2026.3744016
“In contrast, unlike WM-811K, Mixed38 is an unlabeled dataset that does not provide a clearly defined single-label scheme [6], [15].”
Gu, S., Lei, Z., Wen, G., Feng, R., Huang, J., Huang, Y., Zhang, L., & Chen, X. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105413
Lightweight Wafer Defect Classification Based on Improved MobileNetV2 Embedded with ECA Mechanism
Gong, X., & Li, Z. (2026) · IEEE International Conference on Artificial Intelligence, Computer Science and Information Processing (AICSIP) · doi:10.1109/aicsip69702.2026.11744024
“…10].Ram et al. [ 11 ]proposed an enhanced deep convolutional neural network (DCNN) for wafer defect classification, which delivers better performance than conventional CNNs. Wang et al. [12] proposed DC-Net with deformable convolutions for flexible feature sampling and background noise suppression.”
Automated FNN Design for Defect Detection via Multiobjective Optimization
Li, N., Ma, L., Qian, Y., Xue, B., & Zhang, M. (2026) · Genetic and evolutionary computation · doi:10.1007/978-981-95-9155-8_10
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.