MemoryMamba: Memory-Augmented State Space Model for Defect Recognition

TL;DR

MemoryMamba is a novel memory-augmented state space model that significantly improves defect recognition in manufacturing by effectively handling complex, varied, and limited defect data scenarios.

Contribution

It introduces MemoryMamba, integrating memory mechanisms with state space models to enhance defect detection capabilities in manufacturing settings.

Findings

Outperforms existing defect recognition models across multiple datasets.

Effectively handles limited and imbalanced defect data.

Captures complex defect characteristics for improved accuracy.

Abstract

As automation advances in manufacturing, the demand for precise and sophisticated defect detection technologies grows. Existing vision models for defect recognition methods are insufficient for handling the complexities and variations of defects in contemporary manufacturing settings. These models especially struggle in scenarios involving limited or imbalanced defect data. In this work, we introduce MemoryMamba, a novel memory-augmented state space model (SSM), designed to overcome the limitations of existing defect recognition models. MemoryMamba integrates the state space model with the memory augmentation mechanism, enabling the system to maintain and retrieve essential defect-specific information in training. Its architecture is designed to capture dependencies and intricate defect characteristics, which are crucial for effective defect detection. In the experiments, MemoryMamba was evaluated across four industrial datasets with diverse defect types and complexities. The model consistently outperformed other methods, demonstrating its capability to adapt to various defect recognition scenarios.