Cycle-Consistency Uncertainty Estimation for Visual Prompting based One-Shot Defect Segmentation

TL;DR

This paper introduces a cycle-consistency based uncertainty estimation method for visual prompting in one-shot defect segmentation, improving adaptability and reducing over-confidence in unknown defect detection.

Contribution

It proposes a novel cycle-consistency approach to estimate uncertainty in visual prompting, enhancing one-shot defect segmentation without complex ensemble methods.

Findings

Achieved a yield rate of 0.9175 in the VISION24 challenge.

Effectively estimates uncertainty to improve defect detection accuracy.

Addresses over-confidence problem in visual prompting methods.

Abstract

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.