Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection

TL;DR

This paper introduces CMAFNet, a novel cross-modal network that effectively detects small transmission line defects by purifying and fusing RGB and depth data, significantly improving accuracy and efficiency over existing methods.

Contribution

The paper proposes a new purify-then-fuse paradigm with a semantic recomposition module and contextual semantic integration framework for small-object defect detection in RGB-D data.

Findings

CMAFNet achieves 32.2% mAP@50 on TLRGBD benchmark, outperforming baselines.

A lightweight variant reaches 24.8% mAP50 at 228 FPS, surpassing YOLO-based detectors.

The method effectively suppresses modality noise and enhances structural semantic reasoning.

Abstract

Transmission line defect detection remains challenging for automated UAV inspection due to the dominance of small-scale defects, complex backgrounds, and illumination variations. Existing RGB-based detectors, despite recent progress, struggle to distinguish geometrically subtle defects from visually similar background structures under limited chromatic contrast. This paper proposes CMAFNet, a Cross-Modal Alignment and Fusion Network that integrates RGB appearance and depth geometry through a principled purify-then-fuse paradigm. CMAFNet consists of a Semantic Recomposition Module that performs dictionary-based feature purification via a learned codebook to suppress modality-specific noise while preserving defect-discriminative information, and a Contextual Semantic Integration Framework that captures global spatial dependencies using partial-channel attention to enhance structural semantic reasoning. Position-wise normalization within the purification stage enforces explicit reconstruction-driven cross-modal alignment, ensuring statistical compatibility between heterogeneous features prior to fusion. Extensive experiments on the TLRGBD benchmark, where 94.5% of instances are small objects, demonstrate that CMAFNet achieves 32.2% mAP@50 and 12.5% APs, outperforming the strongest baseline by 9.8 and 4.0 percentage points, respectively. A lightweight variant reaches 24.8% mAP50 at 228 FPS with only 4.9M parameters, surpassing all YOLO-based detectors while matching transformer-based methods at substantially lower computational cost.