SOURCE-LINKED INTELLIGENCE

LoRA Enhanced Contrastive Learning with SAS Vision Transformers

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, background clutter, and human-in-the-loop assessment. We adapt DINOv3 Vision Transformer (ViT) models to underwater SAS ATR using a three-stage parameter-efficient framework. Stage 1 uses Low-Rank Adaptation (LoRA) while freezing the ViT backbone, bridging the gap between natural-image pretraining and underwater acoustic propagation. Stage 2 uses hard-negative mining to strengthen the decision boundary against acoustic mimics, i

Read original source ↗ Open in workspace

recordType

paper

region

Global