Network Knowledge Prior Guided Learning for Data-Efficient Surface Defect Detection

TL;DR

This paper introduces a knowledge-guided loss function that improves data efficiency and interpretability in surface defect detection by aligning saliency maps during training, leading to better accuracy and more human-understandable explanations.

Contribution

It proposes a novel multi-task learning framework that incorporates saliency map consistency as a regularizer, enhancing defect detection performance and interpretability without extra inference costs.

Findings

Enhanced accuracy and AP on multiple defect datasets.

Saliency maps become more concentrated and human-interpretable.

Improved model robustness and trustworthiness.

Abstract

Deep learning-based methods have become the de facto standard for industrial defect detection. However, their data-hungry nature and inherent "black-box" characteristics often lead to performance bottlenecks and limited trustworthiness in real-world applications. To address these challenges, this paper proposes a novel knowledge-guided loss function that seamlessly integrates model interpretability into the training process without incurring any additional inference cost. Our method operates in two phases: first, a primary classification network is trained, and its explanations, in the form of saliency maps, are generated as prior knowledge. Second, a multi-task learning framework is established, where the main task performs classification, and an auxiliary task imposes consistency between the saliency maps of the final model and the primary model. This consistency is enforced by a dedicated knowledge-guided loss term, effectively acting as a powerful regularizer to steer the model towards robust feature representations. Extensive experiments on multiple public defect datasets demonstrate that our approach consistently enhances the performance of baseline models in terms of accuracy and AP. Moreover, visual analysis reveals that the proposed method yields more concentrated and human-intelligible saliency maps. This work presents a simple yet effective paradigm for bridging the gap between model performance and interpretability, paving the way for more reliable and high-performing vision systems in industrial quality inspection.