Search papers, labs, and topics across Lattice.
This paper introduces WSA-Net, a lightweight deep learning framework for subsurface defect detection in Ground Penetrating Radar (GPR) data, specifically targeting weak hyperbolic signatures with low signal-to-clutter ratios. WSA-Net employs partial convolutions for signal preservation, heterogeneous grouping attention for clutter suppression, geometric reconstruction to sharpen hyperbolic arcs, and context anchoring to resolve semantic ambiguities. Experiments on the RTST dataset demonstrate that WSA-Net achieves 0.6958 mAP@0.5 and 164 FPS with only 2.412 M parameters, showing improved detection of faint subsurface defects.
You don't need massive models to find tiny cracks: a signal-aware lightweight architecture can outperform heavier detectors in identifying faint subsurface defects in GPR data.
Subsurface defect detection via Ground Penetrating Radar is challenged by"weak signals"faint diffraction hyperbolas with low signal-to-clutter ratios, high wavefield similarity, and geometric degradation. Existing lightweight detectors prioritize efficiency over sensitivity, failing to preserve low-frequency structures or decouple heterogeneous clutter. We propose WSA-Net, a framework designed to enhance faint signatures through physical-feature reconstruction. Moving beyond simple parameter reduction, WSA-Net integrates four mechanisms: Signal preservation using partial convolutions; Clutter suppression via heterogeneous grouping attention; Geometric reconstruction to sharpen hyperbolic arcs; Context anchoring to resolve semantic ambiguities. Evaluations on the RTSTdataset show WSA-Net achieves 0.6958 mAP@0.5 and 164 FPS with only 2.412 M parameters. Results prove that signal-centric awareness in lightweight architectures effectively reduces false negatives in infrastructure inspection.
