AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learn To Cluster Faces via Pairwise Classification

Junfu Liu, Di Qiu, Pengfei Yan, Xiaolin Wei

ICCV 2021 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering · 15 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 weighted-neighbor features to the pair classifier input (ablation)pairwise classifier · MS-Celeb-1M (584K)classifier accuracy: 84.7 -> 95.2Improved
concatenate original features with weighted-neighbor features (combined) (ablation)pairwise classifier · MS-Celeb-1M (584K)classifier accuracy: 95.2 -> 95.6Improved
use combined features instead of original features (precision) (ablation)pairwise classifier · MS-Celeb-1M (584K)precision: 92.2 -> 95.4Improved
combined features instead of weighted-neighbor only (recall) (ablation)pairwise classifier · MS-Celeb-1M (584K)recall: 97.9 -> 97.5Hurt
add rank weighting to density (power 5 vs power 0) (ablation)pair selection density · MS-Celeb-1M (584K)Pairwise F-score: 88.57 -> 90.67Improved
add rank weighting to density (power 5 vs power 0) (ablation)pair selection density · MS-Celeb-1M (584K)BCubed F-score: 88.3 -> 89.54Improved
raise density power from 5 to 7 (ablation)rank-weighted density · MS-Celeb-1M (584K)Pairwise F-score: 90.67 -> 90.32Hurt
raise density power from 1 to 3 (ablation)rank-weighted density · MS-Celeb-1M (584K)Pairwise F-score: 89.69 -> 90.47Improved
replace graph-level GCN learning with pair-level classificationface clustering · MS-Celeb-1M (584K)inference time: 11.5m -> 1.7mImproved
replace GCN(V+E) with pairwise classificationface clustering · MS-Celeb-1M (5.21M)Pairwise F-score: 79.3 -> 82.41Improved
replace GCN(V+E) with pairwise classificationface clustering · IJB-B (1845 ids)Pairwise F-score: DANet 82.8 vs ours 82.7No clear effect
replace GCN(V+E) with pairwise classificationface clustering · DeepFashionPairwise F-score: 38.47 -> 37.67Hurt

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