Back to Home
arXiv AI··Papers & Tech

Beyond CLIP: Calibrated (Few-Shot) Defect Detection With System One Decision Models

中文摘要

研究人员利用System One决策模型实现校准的少样本缺陷检测,旨在解决传统及CLIP方法在缺陷样本获取上的困难。

English Summary

Researchers introduce System One Decision Models for calibrated few-shot defect detection, addressing the difficulty of acquiring sufficient defective images in CLIP-based methods.

Original Excerpt

arXiv:2610.41199v1 Announce Type: cross Abstract: Cameras and vision sensors are widely used for product and process inspection in manufacturing environments. Traditionally, this process required thousands of images of both nominal and defective products to train such models. Recent research shows that vision transformer (ViT) models, such as CLIP, can reduce this requirement to 50-100 images per nominal and defective class. However, collecting even 50 defective images can be difficult in high-yield or low-volume manufacturing processes. In this paper, we examine the utility of two recently proposed structured decision models (Jev and Clef-Flash) in applications using as few as k=2 reference images per class at inference. In the process, we provide three main contributions: (a) a framework for k-shot learning of these models for image classification/inspection applications; (b) an agentic approach for automatically refining the text descriptions that guide image classification in these decision models; and (c) an approach to calibrate the resulting defect probabilities to improve their reliability for inspection decisions. We test these contributions in five manufacturing case stud…