Wenjiao Deng

Ms. Wenjiao Deng

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 August 2026 in Information
Verified
Journal Article
Open access
PDF file
WDWenjiao Deng
Wenjiao Deng
WXWenhui Xia
Wenhui Xia
TBTao Bian
Tao Bian
YLyunhe li
yunhe li
Low-resolution magnetic tile defect recognition suffers from the loss of texture, edge and fine-grained defect information, which weakens discriminative features and reduces recognition accuracy in industrial inspection. To improve defect recognition under low-resolution imaging conditions, this paper proposes a task-aware low-resolution magnetic tile defect image recognition method based on AMCANet. AMCANet is used as the basic super-resolution reconstruction network, and a fixed high-resolution classifier is introduced during training to construct feature consistency loss and classification task loss. Thus, the reconstructed images are constrained to approach high-resolution images at the pixel level while preserving defect-discriminative features. Experiments on the Magnetic Tile Surface Defect Dataset show that the proposed TA-AMCANet achieves an Accuracy of 0.9065 and a Macro-F1 of 0.8204 under the fixed-classifier evaluation setting, improving on the original AMCANet by 0.3238 and 0.3726, respectively. Further ablation, loss-weight sensitivity, AMCA Block configuration, cross-classifier, degradation robustness, external-dataset generalization, Grad-CAM visualization, and computational complexity experiments verify the effectiveness of the proposed task-aware strategy. The results further indicate that higher pixel-level reconstruction metrics do not necessarily correspond to better downstream defect recognition performance, while TA-AMCANet improves recognition adaptability without introducing additional parameters or inference overhead. The method provides an effective solution for low-resolution industrial defect recognition.