An Incremental Unified Framework for Small Defect Inspection

TL;DR

The paper introduces the Incremental Unified Framework (IUF) for defect inspection that effectively handles new objects in industrial pipelines using a transformer-based approach with semantic optimization, enabling scalable and adaptive defect detection.

Contribution

It proposes a novel incremental learning framework with Object-Aware Self-Attention and Semantic Compression Loss for improved defect inspection in dynamic industrial environments.

Findings

Achieves state-of-the-art performance in defect inspection tasks.

Effectively reduces feature conflict during incremental learning.

Demonstrates robustness in both image and pixel-level defect detection.

Abstract

Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing. Yet, many methods, tailored to specific pipelines, grapple with diverse product portfolios and evolving processes. Addressing this, we present the Incremental Unified Framework (IUF), which can reduce the feature conflict problem when continuously integrating new objects in the pipeline, making it advantageous in object-incremental learning scenarios. Employing a state-of-the-art transformer, we introduce Object-Aware Self-Attention (OASA) to delineate distinct semantic boundaries. Semantic Compression Loss (SCL) is integrated to optimize non-primary semantic space, enhancing network adaptability for novel objects. Additionally, we prioritize retaining the features of established objects during weight updates. Demonstrating prowess in both image and pixel-level defect inspection, our approach achieves state-of-the-art performance, proving indispensable for dynamic and scalable industrial inspections. Our code will be released at https://github.com/jqtangust/IUF.