AI Paper Atlas

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

From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data

Daniel Coelho de Castro, Sebastian Nowozin

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 13 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
use the Bayesian identity model instead of NN-distance or one-class SVM for unknown-person detectionOpenFace embeddings on LFW · LFW unknown person detectionAUC: all methods score 95%+ AUC, ours outperforms by a small marginImproved
add the context model (C=3 vs C=1) (ablation)HDP identity model, identity discovery simulation · Simulated identity discovery (adjusted Rand index)adjusted Rand index: marginal improvements and reduced varianceImproved
process data online (frame by frame) rather than batch or offline (ablation)HDP identity model Gibbs sampler · Simulated identity discovery (adjusted Rand index)adjusted Rand index variance: online processing produced much lower variance than batch or offlineImproved
use the proposed label model instead of NN or label propagation for acquainted identitiessemi-supervised labelling on LFW · LFW semi-supervised labelling (acquaintances)label prediction accuracy: NN and LP performed nearly identically and slightly better than oursHurt
increase the number of labelled training images per acquaintance (1 to 15) (ablation)all labelling methods · LFW semi-supervised labellinglabel prediction accuracy: from 1 to 15 labelled imagesImproved

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