136 / 2025-05-26 16:09:41
Large-Scale Vision Foundation Model with Supervised Contrastive Learning-Assisted Fine-Tuning for Wafer Map Mixed Defect Recognition
wafer map,mixed defect,large-scale vision foundation model,supervised contrastive learning (SCL)
全文待审
Shulong Gu / Xi'an Jiaotong University
Zihao Lei / Xi'an Jiaotong University
Guangrui Wen / Xi'an Jiaotong University
Rui Feng / East China Institute of Photo-Electron IC
Di Zhao / Xi'an Jiaotong University
Yunpeng Xu / Xi'an Jiaotong University
The single or mixed defects in wafer maps reflect critical problems in semiconductor manufacturing processes, thus their accurate recognition plays a pivotal role in root cause analysis of anomalies and process stability maintenance. The increasing complexity of mixed-type defects poses new challenges to the feature extraction capability and learning capability of current vision models. To address this challenge, we propose WM-EVA-ViT: a transferred pre-trained large-scale vision foundation model with supervised contrastive learning (SCL)-assisted fine-tuning for wafer map mixed defect recognition (WMMDR). The vision foundation model demonstrates accelerated learning capabilities during the fine-tuning process for defect feature extraction, leveraging its superior general visual feature extraction capacities. Furthermore, a SCL-assisted fine-tuning method is proposed, which enhances class-specific feature discrimination through contrastive learning with class label informed constraints. Experimental results on a real-world dataset validate the effectiveness and superiority of the proposed method. Besides, this method offers novel perspectives for WMMDR in the era of large-scale models.
重要日期
  • 会议日期

    08月01日

    2025

    08月04日

    2025

  • 06月15日 2025

    初稿截稿日期

主办单位
中国机械工程学会设备智能运维分会
承办单位
新疆大学
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询