提出安全跨条件序列视觉定位的验证方法，保障机器人定位可靠性。
SAFEVPR: Patch-Based Conformal Verification for Safe Cross-Condition Sequence Visual Place Recognition
- 用DINOv2特征和MNN匹配得分替代传统相似度，提升跨条件鲁棒性
- 在23组跨条件测试中均满足10%错误接受率，平均正确率75%
- 适合高安全性要求的机器人定位场景，尤其纹理重复区域
基于序列的视觉定位（VPR）在SLAM和机器人重定位中需判断是否接受检索到的最优候选。共形预测是该接受/拒绝决策的理想框架，但其有限样本保证依赖校准与部署数据的可交换性，这在跨条件部署时被破坏。本文提出SAFEVPR，一种无需训练的验证-校准流程，用于安全跨条件序列VPR。SAFEVPR将标准骨干网络的余弦相似度替换为基于冻结DINOv2 ViT特征的互近邻（MNN）局部匹配得分，并以蒙德里安共形学习-先验后测试（Mondrian conformal LTT）替代传统平滑校准，对得分分箱分别拟合邦弗朗尼校正后的阈值。在可交换条件下，这些阈值可提供有限样本的假发现率（FDR）控制；在条件偏移下，我们按部署情况评估其经验有效性。在Oxford RobotCar、NCLT和St Lucia数据集的23个跨条件设置中，使用三个冻结的VPR骨干模型，SAFEVPR在全部23组设置中均满足目标FDR α = 0.10，平均接受后FDR为0.014，平均真阳性率（TPR）为0.75。结果表明，仅靠原始判别能力不足以保证共形有效性：AnyLoc-VLAD和Super-Point+LightGlue在相同校准下达到相近的受试者工作特征曲线下面积（AUROC），但失败更多设置。在无纹理重复场景中，SAFEVPR能安全拒绝不可靠匹配。代码已开源：https://github.com/Hasar12139/SafeVPR。
原文摘要 · Abstract (English)
Sequence-based visual place recognition (VPR) for SLAM and robot relocalization must decide whether the retrieved top-1 candidate is safe to accept. Conformal prediction is a natural framework for this accept/reject decision, but its finite-sample guarantees rely on exchangeability between calibration and deployment (test) data, which is violated under cross-condition deployment. We introduce SAFEVPR, a non-trainable verification-and-calibration pipeline for safe cross-condition sequence VPR. SAFEVPR replaces the standard backbone cosine similarity with a mutual-nearest-neighbour (MNN) patch-matching score computed from frozen DINOv2 ViT features, and replaces flat Learn-Then-Test calibration with Mondrian conformal LTT, fitting separate Bonferroni-corrected thresholds across score bins. Under exchangeability, these thresholds would provide finite-sample false-discovery-rate (FDR) control; under condition shift, we evaluate empirical validity per deployment. Across 23 cross-condition setups from Oxford RobotCar, NCLT, and St Lucia datasets, using three frozen VPR backbones, SAFEVPR is empirically valid on 23/23 setups at target FDR alpha = 0.10, achieving mean accepted FDR 0.014 and mean true-positive rate (TPR) 0.75. The results show that raw discrimination alone is not sufficient for conformal validity: AnyLoc-VLAD and Super-Point+LightGlue reach comparable area under the receiver operating characteristic curve (AUROC) but fail more setups under the same calibration. On textureless repetitive scenery, SAFEVPR safely abstains rather than accepting unreliable matches. Code is available at https://github.com/Hasar12139/SafeVPR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。