Small Object Few-shot Segmentation for Vision-based Industrial Inspection

TL;DR

This paper introduces SOFS, a novel few-shot segmentation model tailored for small defects in industrial inspection, addressing challenges of semantic distortion and false positives without retraining.

Contribution

The paper proposes a small object FSS model that avoids image resizing and uses prototype intensity downsampling, along with an abnormal prior map and a mixed Dice loss to improve defect localization.

Findings

SOFS outperforms existing FSS methods on industrial defect datasets.

The model effectively reduces false positives in small object segmentation.

Experimental results demonstrate superior accuracy and robustness of SOFS.

Abstract

Vision-based industrial inspection (VII) aims to locate defects quickly and accurately. Supervised learning under a close-set setting and industrial anomaly detection, as two common paradigms in VII, face different problems in practical applications. The former is that various and sufficient defects are difficult to obtain, while the latter is that specific defects cannot be located. To solve these problems, in this paper, we focus on the few-shot semantic segmentation (FSS) method, which can locate unseen defects conditioned on a few annotations without retraining. Compared to common objects in natural images, the defects in VII are small. This brings two problems to current FSS methods: 1 distortion of target semantics and 2 many false positives for backgrounds. To alleviate these problems, we propose a small object few-shot segmentation (SOFS) model. The key idea for alleviating 1 is to avoid the resizing of the original image and correctly indicate the intensity of target semantics. SOFS achieves this idea via the non-resizing procedure and the prototype intensity downsampling of support annotations. To alleviate 2, we design an abnormal prior map in SOFS to guide the model to reduce false positives and propose a mixed normal Dice loss to preferentially prevent the model from predicting false positives. SOFS can achieve FSS and few-shot anomaly detection determined by support masks. Diverse experiments substantiate the superior performance of SOFS. Code is available at https://github.com/zhangzilongc/SOFS.