提出新评估方法，发现视觉定位模型常靠环境条件而非真实位置匹配。
Are Visual Place Recognition Models Recognizing Places or Conditions? Distractor-Augmented Evaluation and Condition Suppression
- 引入带干扰项的召回率评估，量化环境相似性对定位的影响
- 在11种方法、6个数据集上，干扰项鲁棒性排名与传统召回率不同
- 通过抑制环境信息可提升抗干扰能力，适合长期定位场景
长期视觉位置识别（VPR）通常在不同条件间进行查询与数据库匹配。然而，众包地图数据库可能混合不同条件，包含与查询环境相似但地点不同的图像。在这种干扰下，模型可能依赖条件相似性而非位置一致性进行检索。我们指出，这源于现有VPR方法的判别力使其编码光照、天气和季节等条件信息。为此，我们提出“带干扰项召回率”（DAR）以分离并量化干扰影响，并采用条件抑制策略从描述符中移除条件信息。在11种方法和6个数据集上，DAR@1排名与标准召回率（R@1）显著不同；使用INLP和LEACE进行条件抑制能普遍提升DAR@1，同时不降低R@1。表明干扰鲁棒性独立于传统检索性能，可通过抑制条件信息加以改善。
原文摘要 · Abstract (English)
Long-term Visual Place Recognition (VPR) is typically evaluated by matching queries from one condition against a database from another. Crowdsourced map databases, however, may mix conditions and include images that resemble the query in condition but depict different places. In the presence of these distractors, a method may retrieve by condition similarity rather than place identity. We argue that this susceptibility arises because the discriminability of VPR methods allows them to encode information such as illumination, weather, and seasonal appearance in their descriptors. We therefore introduce Distractor-Augmented Recall (DAR) to isolate and quantify the effect of distractors, and propose condition suppression to remove condition information from VPR descriptors. Across eleven methods and six datasets, method rankings under DAR@1 differ from those under Recall@1 (R@1), while applying INLP and LEACE as condition suppression methods generally improves DAR@1 without reducing R@1. Thus, distractor robustness is distinct from standard retrieval performance and can be improved by suppressing condition information.
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。