通过循环一致性检测视觉提示中的不确定性，提升新缺陷识别可靠性。
Cycle-Consistency Uncertainty Estimation for Visual Prompting based One-Shot Defect Segmentation
- 用循环一致性检验提示恢复能力，评估模型对未知缺陷的置信度。
- 在VISION24挑战中实现0.9175的良率，无需复杂模型或集成方法。
- 适合工业缺陷检测中快速适应新类型缺陷的场景。
工业缺陷检测传统依赖于已知缺陷类型的固定数据集进行监督学习。尽管在封闭集合内有效，但面对新出现的未见缺陷时表现不佳，需频繁重新标注与训练。近期视觉提示技术可通过提供视觉线索自适应推断新类别，解决此问题。然而，现有方法普遍存在过度自信问题，将未知物体误判为已知类别并给出高置信度。为此，本文提出一种基于循环一致性的不确定性估计方法，通过检验模型能否准确从预测结果还原原始提示来评估其可信度。具体地，计算还原后的提示掩码与原始提示掩码之间的平均交并比（mIoU）。该方法无需复杂设计或多网络集成，在VISION24一次示例工业挑战中达到0.9175的良率。
原文摘要 · Abstract (English)
Industrial defect detection traditionally relies on supervised learning models trained on fixed datasets of known defect types. While effective within a closed set, these models struggle with new, unseen defects, necessitating frequent re-labeling and re-training. Recent advances in visual prompting offer a solution by allowing models to adaptively infer novel categories based on provided visual cues. However, a prevalent issue in these methods is the over-confdence problem, where models can mis-classify unknown objects as known objects with high certainty. To addresssing the fundamental concerns about the adaptability, we propose a solution to estimate uncertainty of the visual prompting process by cycle-consistency. We designed to check whether it can accurately restore the original prompt from its predictions. To quantify this, we measure the mean Intersection over Union (mIoU) between the restored prompt mask and the originally provided prompt mask. Without using complex designs or ensemble methods with multiple networks, our approach achieved a yield rate of 0.9175 in the VISION24 one-shot industrial challenge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。