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

• URL: http://arxiv.org/abs/2605.17780v1
• Date: Mon, 18 May 2026 02:59:33 GMT
• Title: Network Knowledge Prior Guided Learning for Data-Efficient Surface Defect Detection
• Abstract summary: This paper proposes a novel knowledge-guided loss function that seamlessly integrates model interpretability into the training process.<n>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.<n>Experiments on multiple public defect datasets demonstrate that our approach consistently enhances the performance of baseline models in terms of accuracy and AP.
• Score: 3.467019758110102
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• A Knowledge-Informed Pretrained Model for Causal Discovery [61.8885572392623]
  Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes.<n>We propose a knowledge-informed pretrained model for causal discovery that integrates weak prior knowledge as a principled middle ground.<n>Our model adopts a dual source encoder-decoder architecture to process observational data in a knowledge-informed way.
  arXiv  Detail & Related papers  (2026-03-21T14:59:41Z)
• LVLM-Aided Alignment of Task-Specific Vision Models [49.96265491629163]
  Small task-specific vision models are crucial in high-stakes domains.<n>We introduce a novel and efficient method for aligning small task-specific vision models with human domain knowledge.<n>Our method demonstrates substantial improvement in aligning model behavior with human specifications.
  arXiv  Detail & Related papers  (2025-12-26T11:11:25Z)
• Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification [59.59359638389348]
  We propose a Dual-level Modality Debiasing Learning framework that implements debiasing at both the model and optimization levels.<n>Experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model.
  arXiv  Detail & Related papers  (2025-12-03T12:43:16Z)
• Provenance Networks: End-to-End Exemplar-Based Explainability [0.0]
  We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability.<n>Provenance networks learn to link each prediction directly to its supporting training examples as part of the model's normal operation.<n>It addresses critical challenges in modern deep learning, including model opaqueness, hallucination, and the assignment of credit to data contributors.
  arXiv  Detail & Related papers  (2025-10-03T01:48:38Z)
• Rethinking Evaluation of Infrared Small Target Detection [105.59753496831739]
  This paper introduces a hybrid-level metric incorporating pixel- and target-level performance, proposing a systematic error analysis method, and emphasizing the importance of cross-dataset evaluation.<n>An open-source toolkit has be released to facilitate standardized benchmarking.
  arXiv  Detail & Related papers  (2025-09-21T02:45:07Z)
• Reasoning Inconsistencies and How to Mitigate Them in Deep Learning [4.124590489579409]
  This thesis contributes two techniques for detecting and quantifying predictive inconsistencies.<n>To mitigate inconsistencies from biases in training data, this thesis presents a data efficient sampling method.<n>Finally, the thesis offers two techniques to optimize the models for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-04-03T13:40:55Z)
• The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing [0.043512163406552]
  This study introduces a novel method called "The Fairness Stitch" to enhance fairness in deep learning models. We conduct a comprehensive evaluation of two well-known datasets, CelebA and UTKFace. Our findings reveal a notable improvement in achieving a balanced trade-off between fairness and performance.
  arXiv  Detail & Related papers  (2023-11-06T21:14:37Z)
• On Modality Bias Recognition and Reduction [70.69194431713825]
  We study the modality bias problem in the context of multi-modal classification. We propose a plug-and-play loss function method, whereby the feature space for each label is adaptively learned. Our method yields remarkable performance improvements compared with the baselines.
  arXiv  Detail & Related papers  (2022-02-25T13:47:09Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.