融合迁移学习与测试时增强的铝型材瑕疵识别方法

打开文本图片集

中图分类号：TP391 文献标志码：A

Aluminum profile defect recognition method integrating transfer learning and test-time augmentation

HUANG Qinglan， YOU Guirong，LE Ningli， ZHENG Jiafang （Information Technology Center，Fujian Business University，Fuzhou 35OO12，China）

Abstract：To address the challenges of significant variation in aluminum profile defect sizes，low recognition rates，and difficulties in deploying detection systems on edge devices，a lightweight defect clasification method integrating transferlearning and test-time augmentation is proposed.First，the pre-trained MobileViT-XXS model is fine-tuned via transfer learning.This involvesadjusting the weightsof the top MobileViT module，the final convolutional layer，and the classification layer. Second，a symmetric weak data augmentation strategy is designed for both the fine-tuning and testing phases，incorporating horizontal flipping and image scaling. During fine-tuning， randomness is introduced with a 50% probability of applying horizontal flipping.Finaly，the model generates independent predictions for each augmented test sample，and the results are fused by averaging the probability outputs.Experimental results demonstrate that under the same fine-tuning strategy，this lightweight approach improves accuracy by 2.74% and the F1- score by 2.81% compared to the baseline MobileViT-XXS transfer learning model without specific augmentation.

Key words： aluminum profile defect recognition； test-time augmentation； MobileViT-XXS； transferlearning

铝型材瑕疵识别是工业质检中的关键环节，传统的人工质检方式效率低下，难以满足现代高效率生产的需求。（剩余5829字）