AI Paper Atlas

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

AHAN: Asymmetric Hierarchical Attention Network for Identical Twin Face Verification

Hoang-Nhat Nguyen

AAAI 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 Hierarchical Cross-Attention (HCA) (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 81.2 -> 87.1Improved
add Facial Asymmetry Attention Module (FAAM) (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 81.2 -> 84.7Improved
add TA-PWCA twin-distractor regularization (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 81.2 -> 89.9Improved
add FAAM on top of HCA (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 87.1 -> 90.4Improved
add TA-PWCA on top of HCA + FAAM (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 90.4 -> 92.3Improved
add HCA on top of FAAM + TA-PWCA (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 90.7 -> 92.3Improved
add FAAM on top of HCA + TA-PWCA (ablation)AHAN (ViT-B baseline) · ND TWIN (Table 4 ablation, labeled hard twin)TVA (%): 91.8 -> 92.3Improved
replace ArcFace (ResNet-100) with AHANface verification · ND TWIN (twin verification)accuracy (%): 88.9 -> 92.3Improved
replace ArcFace with AHAN on hard twin pairsface verification · ND TWIN (hard twin verification)accuracy (%): 85.3 -> 88.5Improved
replace ArcFace with AHAN on general verificationface verification · ND TWIN (general verification)accuracy (%): 98.5 -> 99.1Improved
use plain ViT transformer face model (TransFace) instead of CNN ArcFacebaseline face recognition · ND TWIN (twin verification)accuracy (%): 88.9 -> 85.2Hurt
use twins as distractors instead of random pairs, hard negatives or siblings in regularization (ablation)AHAN regularization · ND TWIN (hard twin verification)accuracy (%)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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