AI Paper Atlas

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

Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face)

El Ouanas Belabbaci, Bhavesh Wani, Philipp Terhörst

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 0 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 semantic quality to magnitude quality (alpha 0 -> 0.5) (ablation)DQM-Face · Single-image benchmarks avgaccuracy (%): 97.38 -> 97.58Improved
fuse magnitude and semantic quality instead of semantic only (ablation)DQM-Face · Single-image benchmarks avgaccuracy (%): 97.48 -> 97.58Improved
add repulsion margin m2 with staged schedule (ablation)DQM-Face · Single-image benchmarks avgaccuracy (%): 97.32 -> 97.58Improved
add repulsion margin m2 with staged schedule (ablation)DQM-Face · IJB-B TAR@FAR=1e-5TAR (%): 87.21 -> 90.68Improved
use fixed strong repulsion margin 0.20 (ablation)DQM-Face · Single-image benchmarks avgaccuracy (%): 97.58 -> 91.49Hurt
staged m2 schedule instead of linear schedule (ablation)DQM-Face · Single-image benchmarks avgaccuracy (%): 97.38 -> 97.58Improved
staged m2 schedule instead of cosine schedule (ablation)DQM-Face · IJB-B TAR@FAR=1e-5TAR (%): 89.20 -> 90.68Improved
staged m2 schedule instead of linear schedule (ablation)DQM-Face · IJB-B TAR@FAR=1e-5TAR (%): 90.97 -> 90.68Hurt
use DQM-Face instead of MagFace on IJB-BMagFace · IJB-B TAR@FAR=1e-5TAR (%): 90.36 -> 91.35Improved
use DQM-Face quality for FIQA instead of MagFace magnitudeMagFace · FIQA LFWpAUC at 30% discard: 0.0076 -> 0.0061Improved
use DQM-Face instead of ElasticFace on single-image benchmarksElasticFace-Arc+ · Single-image benchmarks avgaccuracy (%): 97.53 -> 97.58No clear effect
use semantic-only quality for FIQA (ablation)DQM-Face · FIQA XQLFWpAUC at 30% discard: 0.1373 -> 0.1346Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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