基于 LDDC-GAN的丁基橡胶数据生成模型研究
CSTR:
作者:
作者单位:

(西安工业大学机电工程学院,西安 710021)

作者简介:

耿家锴(2000—),男,山西省阳泉市人,硕士研究生,主要从事图像生成、工业无监督缺陷检测算法研究;闫莉(1973—),女,安徽省亳州市人,博士,教授,博士生导师,主要从事机器视觉、智能检测与质量控制相关研究。

通讯作者:

中图分类号:

TP183

基金项目:

陕西省秦创原“科学家 +工程师”队伍建设项目(2025QCY-KXJ-048).


Butyl Rubber Data Augmentation Algorithm Based on Lightweight Dual?Domain Constrained Generative Adversarial Network
Author:
Affiliation:

(School of Mechatronic Engineering,Xi’an Technological University,Xi’an 710021,CHN)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对工业视觉检测中丁基橡胶样本稀缺、现有生成模型在小样本下易崩溃及属性失真问题,文章提出一种轻量化双域约束生成对抗网络(LDDC-GAN)。该模型引入频域能量对齐机制以抑制模式崩溃,并结合余弦损失对纹理特征进行约束,通过频域与空间域的协同优化,保证生成图像在结构上的连续性和细节的真实性;同时,设计了渐进式通道压缩策略,将模型参数量降低至 4.42 M,显存占用优化至 6.4 GB,并融合改进的 StyleGAN2生成器、判别器架构与动态梯度裁剪策略,在 386张 256×256工业样本上实现了高效收敛。实验结果表明,该模型在 FID和 SSIM指标上均优于当前主流基线模型。

    Abstract:

    A lightweight dual?domain constrained generative adversarial network(LDDC?GAN) is proposed to address the limited availability of butyl rubber samples for industrial visual inspection,as well as issues of mode collapse and attribute distortion in existing generative models under small?sample conditions. This model introduces a frequency?domain energy alignment mechanism to suppress mode collapse and incorporates cosine loss to constrain texture features. By jointly optimizing the frequency and spatial domains,the model ensures structural continuity and realistic details in the generated images. In addition,a progressive channel compression strategy is designed to reduce the model size to 4. 42 M parameters and optimize memory usage to 6. 4 GB. Combined with an improved StyleGAN2?based generator,discriminator architecture,and a dynamic gradient clipping strategy,the model efficiently converged on a dataset of 386 industrial samples of resolution 256×256. The experimental results demonstrate that the proposed model achieved better performance than the current mainstream baseline models,as measured by the FID and SSIM metrics.

    参考文献
    相似文献
    引证文献
引用本文

耿家锴,闫莉,李雨菲,王丹.基于 LDDC-GAN的丁基橡胶数据生成模型研究[J].半导体光电,2025,46(4):705-711. GENG Jiakai, YAN Li, LI Yufei, WANG Dan. Butyl Rubber Data Augmentation Algorithm Based on Lightweight Dual?Domain Constrained Generative Adversarial Network[J].,2025,46(4):705-711.

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2025-04-08
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2025-08-25
  • 出版日期:
文章二维码