AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions

Arslan Ali, Matteo Testa, Tiziano Bianchi, Enrico Magli

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase feature dimension d from 128 to 512 (ablation)BioMetricNet · LFWverification accuracy (%): 99.47 -> 99.80Improved
increase feature dimension d from 128 to 512 (ablation)BioMetricNet · CPLFWverification accuracy (%): 94.89 -> 95.60Improved
increase feature dimension d from 512 to 1024 (ablation)BioMetricNet · LFWverification accuracy (%): 99.80 -> 99.63Hurt
increase feature dimension d from 512 to 1024 (ablation)BioMetricNet · CPLFWverification accuracy (%): 95.60 -> 95.25Hurt
increase latent dimension p from 1 to 16 (ablation)BioMetricNet · LFWverification accuracy (%): 99.80 -> 99.72Hurt
increase latent dimension p from 1 to 16 (ablation)BioMetricNet · CPLFWverification accuracy (%): 95.60 -> 95.43Hurt
increase latent dimension p from 1 to 16 (ablation)BioMetricNet · CFP-FPverification accuracy (%): 99.35 -> 99.47Improved
increase latent dimension p from 1 to 8 (ablation)BioMetricNet · CPLFWverification accuracy (%): 95.60 -> 95.13Hurt
increase latent dimension p from 1 to 3 (ablation)BioMetricNet · CALFWverification accuracy (%): 97.07 -> 97.02No clear effect
replace fixed analytic metric with learned metric regularized to Gaussians, versus ArcFaceBioMetricNet vs ArcFace · CPLFWverification accuracy (%): 92.08 -> 95.60Improved
replace fixed analytic metric with learned metric regularized to Gaussians, versus ArcFaceBioMetricNet vs ArcFace · LFWverification accuracy (%): 99.82 vs 99.80No clear effect
replace fixed analytic metric with learned metric regularized to Gaussians, versus ArcFaceBioMetricNet vs ArcFace · CALFWverification accuracy (%): 95.45 -> 97.07Improved

Later papers that compared with this method

1 later accepted paper reports BioMetricNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy