AI Paper Atlas

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

Attentional Feature-Pair Relation Networks for Accurate Face Recognition

Bong-Nam Kang, Yonghyun Kim, Bongjin Jun, Daijin Kim

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 49 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
add feature-pair bilinear attention without pair selection (ablation)baseline face encoder · LFWaccuracy (%): 99.60 -> 99.71Improved
add feature-pair bilinear attention without pair selection (ablation)baseline face encoder · YTFaccuracy (%): 95.1 -> 96.1Improved
add top-K feature-pair selection layer (K=442) (ablation)AFRN · VGGFace2 validation setaccuracy (%): 95.1 -> 97.4Improved
add top-K feature-pair selection layer (K=442) (ablation)AFRN · YTFaccuracy (%): 96.1 -> 97.1Improved
use K=442 instead of using all pairs (K=1,200) (ablation)AFRN · VGGFace2 validation setaccuracy (%): 2.3% lowerImproved
use feature-pair bilinear attention instead of unitary attention (ablation)AFRN with pair selection · YTFaccuracy (%): 95.3 -> 97.1Improved
use feature-pair bilinear attention instead of co-attention (ablation)AFRN with pair selection · LFWaccuracy (%): 99.63 -> 99.85Improved
add pair selection to AFRN (ablation)AFRN · IJB-A TAR at FAR=0.001TAR: 0.904 -> 0.949Improved
add pair selection to AFRN (ablation)AFRN · IJB-B Rank-1accuracy: 0.923 -> 0.973Improved
add pair selection to AFRN (ablation)AFRN · IJB-B TAR at FAR=0.001TAR: 0.933 -> 0.949Improved
add AFRN without pair selection to baseline encoder (ablation)model A · IJB-A Rank-1accuracy: 0.975 -> 0.981Improved
add pair selection to AFRN (ablation)AFRN · CPLFWaccuracy (%): 91.17 -> 93.48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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