|国家预印本平台
首页|YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Jiawei Hu

计算技术、计算机技术

Jiawei Hu.YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection[EB/OL].(2025-06-26)[2025-07-18].https://arxiv.org/abs/2506.21135.点此复制

评论