YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection

TL;DR

YOLO-FDA is a new surface defect detection framework that enhances detail sensitivity and robustness by integrating hierarchical attention, feature fusion, and a novel fusion module within a YOLO-based architecture.

Contribution

It introduces a hierarchical attention and detail enhancement framework with a novel fusion module and strategies, improving defect detection accuracy and robustness over existing methods.

Findings

Outperforms state-of-the-art methods in accuracy.

Demonstrates robustness across diverse defect types and scales.

Enhances feature detail and contextual representation.

Abstract

Surface defect detection in industrial scenarios is both crucial and technically demanding due to the wide variability in defect types, irregular shapes and sizes, fine-grained requirements, and complex material textures. Although recent advances in AI-based detectors have improved performance, existing methods often suffer from redundant features, limited detail sensitivity, and weak robustness under multiscale conditions. To address these challenges, we propose YOLO-FDA, a novel YOLO-based detection framework that integrates fine-grained detail enhancement and attention-guided feature fusion. Specifically, we adopt a BiFPN-style architecture to strengthen bidirectional multilevel feature aggregation within the YOLOv5 backbone. To better capture fine structural changes, we introduce a Detail-directional Fusion Module (DDFM) that introduces a directional asymmetric convolution in the second-lowest layer to enrich spatial details and fuses the second-lowest layer with low-level features to enhance semantic consistency. Furthermore, we propose two novel attention-based fusion strategies, Attention-weighted Concatenation (AC) and Cross-layer Attention Fusion (CAF) to improve contextual representation and reduce feature noise. Extensive experiments on benchmark datasets demonstrate that YOLO-FDA consistently outperforms existing state-of-the-art methods in terms of both accuracy and robustness across diverse types of defects and scales.