# Rank-1 Identity Consensus Predicts Gallery Enrollment in 1:N Face Matching More Accurately than Score Thresholding

arXiv: https://arxiv.org/abs/2607.12903 · HTML: https://mlsanity.com/paper/2607.12903/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [The Extreme Value Machine](https://mlsanity.com/paper/1506.06112/) (2015)
- [Neural Aggregation Network for Video Face Recognition](https://mlsanity.com/paper/1603.05474/) (2016)
- [Toward Open-Set Face Recognition](https://mlsanity.com/paper/1705.01567/) (2017)
- [Cluster and Aggregate: Face Recognition with Large Probe Set](https://mlsanity.com/paper/2210.10864/) (2022)
- [Deep Heterogeneous Feature Fusion for Template-Based Face Recognition](https://mlsanity.com/paper/1702.04471/) (2017)
- [Impact of Blur and Resolution on Demographic Disparities in 1-to-Many Facial Identification](https://mlsanity.com/paper/2309.04447/) (2023)
- [Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss](https://mlsanity.com/paper/2311.00400/) (2023)
- [Deep CNN Face Matchers Inherently Support Revocable Biometric Templates](https://mlsanity.com/paper/2506.18731/) (2025)
- [Are you In or Out (of gallery)? Wisdom from the Same-Identity Crowd](https://mlsanity.com/paper/2508.06357/) (2025)

## Abstract (arXiv)

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.