Skip to main content
Search

# ARAFT

1 related articles

Subscribe to updates
  1. arXiv

    Invisible perturbations wipe out visual place recognition recall: ARAFT lifts robust R@1 to 47.3 inside a 5-point clean-accuracy budget

    Current DINOv2-based visual place recognition models lose almost all top-1 recall when the query image is imperceptibly perturbed: under a ranking attack, SuperVLAD and BoQ keep at most 0.2% R@1 on four benchmarks. ARAFT fine-tunes a released model with its original metric-learning loss on clean images, a listwise rank loss on each adversarial query's hardest positive, and an anchor that pulls the adversarial descriptor toward the clean descriptor of the frozen pretrained model, selecting checkpoints under a clean-accuracy budget fixed in advance. Within a 5-point validation clean R@1 budget, plain adversarial training has no admissible checkpoint, while ARAFT raises robust R@1 from zero to 47.3 on SuperVLAD and 55.3 on BoQ.

You’re all caught up