Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects

TL;DR

This paper introduces GCANet, a lightweight neural network that combines a transformer encoder with novel attention modules to improve surface defect detection accuracy while maintaining real-time efficiency.

Contribution

The paper proposes a novel global context aggregation network with a Depth-wise Self-Attention module and Channel Reference Attention, enhancing feature representation in lightweight defect detection models.

Findings

Achieves 91.79% Fβw on SD-saliency-900 dataset.

Runs at 272fps on a single GPU.

Outperforms 17 state-of-the-art methods in accuracy-efficiency trade-off.

Abstract

Surface defect inspection is a very challenging task in which surface defects usually show weak appearances or exist under complex backgrounds. Most high-accuracy defect detection methods require expensive computation and storage overhead, making them less practical in some resource-constrained defect detection applications. Although some lightweight methods have achieved real-time inference speed with fewer parameters, they show poor detection accuracy in complex defect scenarios. To this end, we develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The proposed DSA performs element-wise similarity in channel dimension while maintaining linear complexity. In addition, we introduce a novel Channel Reference Attention (CRA) module before each decoder block to strengthen the representation of multi-level features in the bottom-up path. The proposed CRA exploits the channel correlation between features at different layers to adaptively enhance feature representation. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods. Specifically, GCANet achieves competitive accuracy (91.79% $F_{\beta}^{w}$, 93.55% $S_\alpha$, and 97.35% $E_\phi$) on SD-saliency-900 while running 272fps on a single gpu.