A New Contrastive GAN With Data Augmentation for Surface Defect Recognition Under Limited Data

Du, Zongwei; Gao, Liang; Li, Xinyu

doi:10.1109/tim.2022.3232649

Cited by 15 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notable examples include Auto-Encoders (AE) 13,[21][22][23] , which are extensively employed due to their ability to recreate the original image. Similarly, Generative Adversarial Networks (GANs) [14][15][16]24,25 are commonly utilized in this context. However, the very nature of deep neural networks capable of accurately reconstructing normal images often inadvertently leads to plausible reconstructions of anomalous regions as well, thereby limiting the detection accuracy of these methodologies.…”

Section: Related Workmentioning

confidence: 99%

Cosine similarity knowledge distillation for surface anomaly detection

Sheng,

Jing,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The current state-of-the-art anomaly detection methods based on knowledge distillation (KD) typically depend on smaller student networks or reverse distillation to address vanishing representations discrepancy on anomalies. These methods often struggle to achieve precise detection when dealing with complex texture backgrounds containing anomalies due to the similarity between anomalous and non-anomalous regions. Therefore, we propose a new paradigm—Cosine Similarity Knowledge Distillation (CSKD), for surface anomaly detection and localization. We focus on the superior performance of the same deeper teacher and student encoders by the distillation loss in traditional knowledge distillation-based methods. Essentially, we introduce the Attention One-Class Embedding (AOCE) in the student network to enhance learning capabilities and reduce the effect of the teacher–student (T–S) model on response similarity in anomalous regions. Furthermore, we find the optimal models by different classes’ hard-coded epochs, and an adaptive optimal model selection method is designed. Extensive experiments on the MVTec dataset with 99.2% image-level AUROC and 98.2%/94.7% pixel-level AUROC/PRO demonstrate that our method outperforms existing unsupervised anomaly detection algorithms. Additional experiments on DAGM dataset, and one-class anomaly detection benchmarks further show the superiority of the proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

Cosine similarity knowledge distillation for surface anomaly detection

Sheng,

Jing,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…A framework called DefectGAN was introduced in [ 17 ] by using a compositional-layer-based architecture to generate realistic defect images. For data augmentation of surface defects on hot-rolled steel strips, three GANs were trained in [ 18 ], a new GAN called a contrastive GAN was proposed in [ 19 ], and a semi-supervised learning (SSL) defect classification approach based on two different networks of a categorized generative adversarial network (GAN) and a residual network was proposed in [ 20 ]. In order to produce defect images using a large number of defect-free images of commutator cylinder surfaces from industrial sites, a generation technique known as the surface defect generation adversarial network (SDGAN) was introduced in [ 21 ].…”

Section: Previous Work On Data Augmentation Using a Ganmentioning

confidence: 99%

Generating Defective Epoxy Drop Images for Die Attachment in Integrated Circuit Manufacturing via Enhanced Loss Function CycleGAN

Alam

Kehtarnavaz

2023

Sensors

View full text Add to dashboard Cite

In integrated circuit manufacturing, defects in epoxy drops for die attachments are required to be identified during production. Modern identification techniques based on vision-based deep neural networks require the availability of a very large number of defect and non-defect epoxy drop images. In practice, however, very few defective epoxy drop images are available. This paper presents a generative adversarial network solution to generate synthesized defective epoxy drop images as a data augmentation approach so that vision-based deep neural networks can be trained or tested using such images. More specifically, the so-called CycleGAN variation of the generative adversarial network is used by enhancing its cycle consistency loss function with two other loss functions consisting of learned perceptual image patch similarity (LPIPS) and a structural similarity index metric (SSIM). The results obtained indicate that when using the enhanced loss function, the quality of synthesized defective epoxy drop images are improved by 59%, 12%, and 131% for the metrics of the peak signal-to-noise ratio (PSNR), universal image quality index (UQI), and visual information fidelity (VIF), respectively, compared to the CycleGAN standard loss function. A typical image classifier is used to show the improvement in the identification outcome when using the synthesized images generated by the developed data augmentation approach.

show abstract

“…Deep learning-based approaches are generally effective, but they require large amounts of data. GAN-based methods (Niu et al, 2020;Wei et al, 2022;Du et al, 2022;Zhang et al, 2021) are adopted to perform defect sample synthesis for data augmentation. DefectGAN adopts an encoder-decoder structure to synthesize defects by mimicking defacement and restoration processes.…”

Section: Related Workmentioning

confidence: 99%

Datasets and Methods for Boosting Infrastructure Inspection: A Survey on Defect Classification

Yang

Liu

Zhao

et al. 2022

2022 IEEE 17th International Conference on Control &Amp; Automation (ICCA)

View full text Add to dashboard Cite

Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semanticabundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models. Our project page is in https://envision-research.github.io/Defect_Spectrum.

show abstract

A New Contrastive GAN With Data Augmentation for Surface Defect Recognition Under Limited Data

Cited by 15 publications

References 28 publications

Cosine similarity knowledge distillation for surface anomaly detection

Cosine similarity knowledge distillation for surface anomaly detection

Generating Defective Epoxy Drop Images for Die Attachment in Integrated Circuit Manufacturing via Enhanced Loss Function CycleGAN

Datasets and Methods for Boosting Infrastructure Inspection: A Survey on Defect Classification

Contact Info

Product

Resources

About