Anchored Rank-Adversarial Fine-Tuning Pretrained Visual Place Recognition Models

Paper recorded by Signals 4 on 2026-11-03 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-03 on arXiv · recorded by Signals 4 on 2026-11-04

Category: cs.CV · 计算机视觉 · first seen 2026-11-04

Abstract

Visual place recognition (VPR) localises a camera by retrieving similar geo-tagged images, and current foundation-model VPR models are accurate across cities, seasons and illumination, but not robust to adversarial perturbations: under a white-box attack on the ranking at an imperceptible budget of 1/255, SuperVLAD and BoQ keep at most 0.2% top-1 recall (R@1) on four benchmarks. We propose anchore

Read on arXiv →