AI 中文总结
研究 1:N 人脸识别中判断某人是否在图库注册的问题，核心方法是基于多个匹配器秩一致性的 1-一致性，贡献是在多场景压力测试中表现出色，能达神谕级别准确性且无需事先了解探测条件。
AI 中文摘要
在实际的 1:N 人脸识别中，对于每个探测都有一个关键问题：此人是否在图库中注册？风险高且不对称。拒绝匹配者在场（MP）的探测会失去有效线索；接受匹配者不在场（MA）的探测会使每个返回的候选者成为错误识别，最坏的情况是错误逮捕。大多数方法对匹配分数进行阈值处理，但分数会随图像质量、图库大小和组成而大幅变化，使得在实际条件下部署前固定的阈值很脆弱。我们之前的工作引入了 1-一致性，这是唯一基于多个独立训练的匹配器的秩一致性的方法：如果所有匹配器都返回相同的秩-1 身份，则将探测标记为 MP。这项工作在跨越四个质量级别和两个结构轴（每个身份的图像数量和总注册身份数量）的 36 种（图库，探测质量）场景中对 1-一致性进行压力测试。我们与两种分数阈值法进行基准测试，这两种方法涵盖了任何部署阈值可能达到的范围。固定分数阈值法（FST）在基线条件下校准一次，随着质量下降不对称地崩溃：MP 召回率降至 2%以下，而 MA 召回率接近 100%。神谕分数阈值法（OST）针对每个场景重新调整，是理论上任何阈值所能达到的最佳效果，但对于降级的探测，1-一致性无需调整就能与之匹配。两者主要在错误类型上有所不同（OST 有利于 MP 召回率，1-一致性有利于 MA 召回率），但在一个轴上，1-一致性不仅与神谕匹配：当它将探测标记为 MP 时，在严重降级情况下，它 97%-100%的时间返回正确的匹配对象，而 OST 为 66%-84%。简而言之，1-一致性在无需不可能的要求下提供了神谕级别的准确性：它不设置阈值，因此无需事先了解探测将遇到的条件，这使其具有实用性。
英文摘要
In operational 1:N face identification, a crucial question arises for each probe: is this person enrolled in the gallery or not? The stakes are high and asymmetric. Rejecting a mate-present (MP) probe loses a valid lead; accepting a mate-absent (MA) probe makes every returned candidate a false identification, at worst a wrongful arrest. Most approaches threshold match scores, but scores shift substantially with image quality and gallery size and composition, making thresholds fixed before deployment brittle under realistic conditions. Our prior work introduced 1-consistency, the only method based on rank consensus across multiple independently trained matchers: a probe is labeled MP if all matchers return the same rank-1 identity. This work stress-tests 1-consistency across 36 (gallery, probe quality) scenarios spanning four quality levels and two structural axes: images per identity and total enrolled identities. We benchmark against two score-thresholding methods that bracket what any deployed threshold could achieve. Fixed Score-Thresholding (FST), calibrated once on baseline conditions, collapses asymmetrically as quality degrades: MP recall falls below 2% while MA recall holds near 100%. Oracle Score-Thresholding (OST), re-tuned per scenario, is the best any threshold could theoretically do, yet for degraded probes 1-consistency matches it with zero tuning. The two differ mainly in error type (OST favors MP recall, 1-consistency favors MA recall), but on one axis 1-consistency does not merely match the oracle: when it labels a probe MP, it returns the correct mate 97-100% of the time versus OST's 66-84% under severe degradation. In short, 1-consistency delivers oracle-level accuracy without the impossible requirement: it sets no threshold, so it needs no advance knowledge of the conditions a probe will arrive in, which is what makes it usable.
Comments10 pages, 8 figures, 5 tables
