Hierarchical Scale Enhancement Network With Contrast Encoding for Few-Shot Liquid Crystal Display Defect Detection

Abstract

As the most crucial medium for multimedia presentation, liquid crystal display (LCD) is integral to numerous industries, making precise defect detection essential to ensure display quality and user experience. However, high-accuracy defect detection of LCDs remains a significant challenge due to large-scale variations and high interclass similarity, especially under the setting of few-shot learning. To address these challenges, we propose a few-shot defect detection network, namely, HiSCAD-Net. Specifically, we design an auxiliary branch for hierarchical scale enhancement, which introduces additional objectness and classification constraints based on object pyramid sampling. Moreover, to tackle the misclassification caused by interclass similarity, we introduce an object-level contrastive encoding (OCE) to encourage class-discriminative feature learning, which enforces zero distance between objects of the same class, while ensuring that the distance between objects of different classes remains above a predefined threshold. Finally, we propose an adaptive decoupling module (ADM) to mitigate interference between classification and regression tasks given limited training samples, thereby improving both the tasks during decoding. To support benchmarking in few-shot LCD (FSLCD) defect detection, we propose a new dataset named FSLCD. Experimental results on the FSLCD, NEU-DET, and PKU-Market-Phone datasets demonstrate that the proposed model outperforms 18 state-of-the-art methods, validating its effectiveness and generalizability. Notably, in the ten-shot setting, our model achieved a mean average precision (mAP) of 62.0%, surpassing the state-of-the-art by 10.4%.