.png){kind=icon}
返回
A multi-stage active learning framework with an instance-based sample selection algorithm for steel surface defect
.png){kind=icon}
PRE
AI
DOI：10.1016/j.aei.2024.103080.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The application of deep learning (DL) for high-precision inspection to identify and locate the positions of each type of steel surface defect has demonstrated considerable potential for the quality control of steel products. However, the time-consuming and labor-intensive nature of manually labeling large amounts of data has limited DL's broader deployment in this field. While traditional active learning methods can select the most valuable labels based on the amount of information, they fail to consider the positional and categorical information during the information computation process, thereby preventing the extraction of spatial information with multiple defects simultaneously. To address this challenge, this paper proposes a multi-stage active learning framework with an instance-based sample selection algorithm (MALF) for steel surface defects. Firstly, a soft weighted label assignment with prior information is constructed with the objective of achieving stable training and highprecision instance detection with a minimal amount of label annotation. Furthermore, when provided with high-precision instances, an independent evidence branch utilizing a reweighted Dirichlet distribution is capable of generating epistemic uncertainty with remarkable efficiency. Besides, a methodology based on diversity has been devised to ascertain the similarity with instance data as a diversity criterion, thereby obtaining detailed spatial information in multi-defect images. The results of experiments conducted on a variety of benchmark methods indicate that MALF is capable of filtering out more informative images for annotation while achieving higher accuracy with the same sample size.
Keyword:
High-precision detection
Active learning
Multi-stage sample selection
Label assignment
Multi-defect instance
期刊
IF:
9.9
论文数:
4.1K
被引数:
1.7W
机构
引用论文
Graph-Based Active Learning With Uncertainty and Representativeness for Industrial Anomaly Detection
PREAI
分享收藏An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features融合多个层次特征的端到端钢表面缺陷检测方法
OAAI
OAAI分享收藏Surface defect detection and classification of steel using an efficient Swin Transformer使用高效Swin变压器对钢的表面缺陷进行检测和分类
PREAI
分享收藏Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup通过不确定性感知混合实现高效的计算知识蒸馏.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容