Coarse-to-Fine Few-Shot Defect Recognition With Dynamic Weighting and Joint Metric

Song, Yiguo; Liu, Zhenyu; Ling, Shiquan; Tang, Ruining; Duan, Guifang; Tan, Jianrong

doi:10.1109/tim.2022.3193204

Cited by 17 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, this paper proposes a position update strategy based on a dynamic weighting approach (Song et al 2022), which introduces a learning rate 𝑤 for gray wolves 𝜔 as shown in Eq.22:…”

Section: Update the Positionmentioning

confidence: 99%

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

Chen

2023

Preprint

View full text Add to dashboard Cite

Automatic tooth arrangement and path planning plays an essential role in computer-aided orthodontic treatment. However, state-of-the-art methods have some shortcomings: low efficiency, excessive cost of displacements or collisions and insufficient accuracy. To address these issues, this paper proposes an innovative orthodontic path planning method based on the improved gray wolf optimization algorithm, which is called OPP-IGWO. First, the tooth model is preprocessed to obtain initial pose in which each tooth is segmented and built up with an oriented bounding box (OBB). Next, the target pose of each tooth is determined through the ideal dental arch curve and the optimal jaw principle. Finally, the path from the initial pose to the target pose of each tooth is planned based on IGWO, which is improved mainly from three aspects: (1) The greedy idea is adopted to initialize the gray wolf population based on dental interpolation. (2) The linear convergence factor in the traditional gray wolf optimization algorithm (GWO) is replaced with a non-linear convergence factor. (3) We propose a position update strategy based on a dynamic weighting approach, which introduces a learning rate for each gray wolf. The experimental results show that our OPP-IGWO method outperforms the state-of-the-art methods. Compared with improved genetic algorithm (IGA), normal simplified mean particle swarm optimization algorithm (NSMPSO), multiparticle improved swarm optimization (Mutil-IPSO) and improved artificial bee colony algorithm (IABC), the OPP-IGWO has an improvement on performance by 14.22%, 11.46%, 6.32% and 5.27% respectively.

show abstract

Section: Update the Positionmentioning

confidence: 99%

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

Chen

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Few-shot learning requires transferring prior knowledge from the source domain to the target domain, and then using contrastive learning and the support set created by a small amount of data to accomplish the classification task. Reference [3] proposed a few-shot defect recognition (FSDR) for real industrial scenarios with insufficient training samples. The proposed method achieves defect recognition by a coarse-to-fine manner with a dynamic weighting and joint metric.…”

Section: Introductionmentioning

confidence: 99%

MGFNet: A Progressive Multi-Granularity Learning Strategy-Based Insulator Defect Recognition Algorithm for UAV Images

Shuang

2023

Drones

View full text Add to dashboard Cite

Due to the low efficiency and safety of a manual insulator inspection, research on intelligent insulator inspections has gained wide attention. However, most existing defect recognition methods extract abstract features of the entire image directly by convolutional neural networks (CNNs), which lack multi-granularity feature information, rendering the network insensitive to small defects. To address this problem, we propose a multi-granularity fusion network (MGFNet) to diagnose the health status of the insulator. An MGFNet includes a traversal clipping module (TC), progressive multi-granularity learning strategy (PMGL), and region relationship attention module (RRA). A TC effectively resolves the issue of distortion in insulator images and can provide a more detailed diagnosis for the local areas of insulators. A PMGL acquires the multi-granularity features of insulators and combines them to produce more resilient features. An RRA utilizes non-local interactions to better learn the difference between normal features and defect features. To eliminate the interference of the UAV images’ background, an MGFNet can be flexibly combined with object detection algorithms to form a two-stage object detection algorithm, which can accurately identify insulator defects in UAV images. The experimental results show that an MGFNet achieves 91.27% accuracy, outperforming other advanced methods. Furthermore, the successful deployment on a drone platform has enabled the real-time diagnosis of insulators, further confirming the practical applications value of an MGFNet.

show abstract

“…However, data collection in real industrial scenarios is difficult and time-consuming, which remains a huge challenge when only a small amount of data can be used. Recently, fewshot recognition (FSR) methods have been gradually explored to achieve precise defect recognition only from a few target samples [10,11]. They train a robust model on known classes with many samples and then achieve the prediction on unknown classes with few samples.…”

Section: Introductionmentioning

confidence: 99%

Cross-domain few-shot defect recognition for metal surfaces

Duan¹,

Song²,

Liu³

et al. 2022

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Defect recognition for metal surface in the industry has attracted more and more attention. However, the defect data scarcity brings a huge challenge for the defect recognition in the real industrial scenario. The traditional few-shot defect recognition method can address this problem when the train data and test data are collected from the same or similar metal surface. While the defect data from the similar metal surfaces is difficult to acquire to a certain extent. In this paper, we introduce a novel task setting which can achieve the few-shot defect recognition by transferring the knowledge across domains. This method consists of two levels: image-level and feature level. In the image-level, the meta-augmentation method is proposed to improve the recognition generalization in each meta-task by joint parameter updating from the original domain and augmented domain. In the feature-level, the class covariance guided feature perturbation method is proposed to perturb the feature distribution for enhancing the cross-domain generalization capability. Extension cross-domain experiments from the textured surface to metal surface show the superior performance of the proposed method compared with other mainstream methods.

show abstract

Coarse-to-Fine Few-Shot Defect Recognition With Dynamic Weighting and Joint Metric

Cited by 17 publications

References 23 publications

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

MGFNet: A Progressive Multi-Granularity Learning Strategy-Based Insulator Defect Recognition Algorithm for UAV Images

Cross-domain few-shot defect recognition for metal surfaces

Contact Info

Product

Resources

About