计算机科学
生成语法
人工智能
过程(计算)
编码(集合论)
深度学习
机器学习
生成模型
数据建模
基线(sea)
训练集
模式识别(心理学)
代码生成
特征提取
数据驱动
标记数据
模板
作者
Xiaoyu Jiang,Zilong Lin,Xiangyin Kong,Jiayu Chen,Zhihuan Song,Min Xie
标识
DOI:10.1109/tase.2025.3641997
摘要
Surface Defect Recognition (SDR) is crucial in the manufacturing industry. Recent advancements in deep learning and computer vision have significantly improved the precision and efficiency of SDR. However, the scarcity of defect samples presents a challenge for training deep learning models, making few-shot learning necessary for the SDR task. For this, this paper explores innovative contributions of Large Generative Models (LGM) to few-shot SDR by integrating Large Language Models (LLM) and Multimodal Generative Models (MGM). We present an LGM-based Training-Free Data Augmentation (LTDA) method to efficiently expand few-shot datasets without additional training. LTDA employs a conditional generation framework that leverages text instructions provided by LLM as conditions to guide the generation process of MGM. Additionally, multiple prompting templates have been designed for LLM to provide more precise instructions, thereby better guiding the conditional generation process. Finally, we employ two strategies for utilizing generated data to accomplish enhanced few-shot SDR by LTDA. The effectiveness of these approaches is demonstrated through two cases of defect recognition on steel surfaces, where the results demonstrate that the proposed method achieves an average accuracy improvement of 29% and 13% over the baseline method. The code will be released at https://github.com/jackiddd/LTDA.
科研通智能强力驱动
Strongly Powered by AbleSci AI