AI Paper Atlas

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

Discriminatively Learned Convex Models for Set Based Face Recognition

Hakan Cevikalp, Golara Ghorban Dordinejad

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 6 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
replace generatively learned affine hull with discriminatively learned affine hull (ablation)AHISD · PaSC Controlverification rate (%): 80.97 -> 88.76Improved
replace generatively learned affine hull with discriminatively learned affine hull (ablation)AHISD · PaSC Handheldverification rate (%): 65.14 -> 77.39Improved
replace generatively learned convex hull with discriminatively learned convex hull (ablation)CHISD · PaSC Controlverification rate (%): 88.48 -> 93.31Improved
replace generatively learned convex hull with discriminatively learned convex hull (ablation)CHISD · PaSC Handheldverification rate (%): 74.01 -> 85.00Improved
replace generatively learned affine hull with discriminatively learned affine hull (ablation)AHISD · YouTube Celebrities (LBP)accuracy (%): 62.0 -> 71.5Improved
replace generatively learned convex hull with discriminatively learned convex hull (ablation)CHISD · YouTube Celebrities (LBP)accuracy (%): 65.7 -> 71.2Improved
replace generatively learned affine hull with discriminatively learned affine hull (ablation)AHISD · ESOGU-285 (LBP features)accuracy (%): 66.8 -> 86.6Improved
replace generatively learned convex hull with discriminatively learned convex hull (ablation)CHISD · ESOGU-285 (LBP features)accuracy (%): 76.6 -> 89.0Improved
replace generatively learned affine hull with discriminatively learned affine hull (ablation)AHISD · ESOGU-285 (CNN features)accuracy (%): 81.32 -> 85.26Improved
replace generatively learned convex hull with discriminatively learned convex hull (ablation)CHISD · ESOGU-285 (CNN features)accuracy (%): 79.82 -> 85.70Improved
replace generatively learned affine hull with discriminatively learned affine hull (ablation)AHISD · COX video-to-video (LBP)accuracy (%): 44.3 -> 55.9Improved
replace generatively learned convex hull with discriminatively learned convex hull (ablation)CHISD · COX video-to-video (LBP)accuracy (%): 44.8 -> 75.1Improved

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