AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective

Jun Dan, Yang Liu, Haoyu Xie, Jiankang Deng, Haoran Xie, Xuansong Xie, Baigui Sun

ICCV 2023 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 75 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 DPAP and EHSM (TransFace)ViT-S · IJB-C TAR@FAR=1E-4 (MS1MV2)TAR: 95.89 -> 96.45Improved
add DPAP and EHSM (TransFace)ViT-L · IJB-C TAR@FAR=1E-4 (Glint360K)TAR: 97.13 -> 97.61Improved
add DPAP and EHSM (TransFace)ViT-L · IJB-C TAR@FAR=1E-5 (Glint360K)TAR: 95.78 -> 96.29Improved
add DPAP and EHSM (TransFace)ViT-L · CFP-FP (Glint360K)accuracy: 99.10 -> 99.32Improved
add DPAP and EHSM (TransFace)ViT-L · LFW (Glint360K)accuracy: 99.82 -> 99.85No clear effect
add SE module (ablation)ViT-S · IJB-C TAR@FAR=1E-4 (MS1MV2)TAR: 95.89 -> 96.12Improved
add DPAP on top of SE (ablation)ViT-S · IJB-C TAR@FAR=1E-4 (MS1MV2)TAR: 96.12 -> 96.30Improved
add EHSM on top of DPAP (ablation)ViT-S · IJB-C TAR@FAR=1E-4 (MS1MV2)TAR: 96.30 -> 96.45Improved
use DPAP instead of Random Erasing (ablation)ViT-S · IJB-C TAR@FAR=1E-6 (MS1MV2)TAR: 83.68 -> 86.60Improved
use DPAP instead of Mixup/CutMix (ablation)ViT-S · IJB-C TAR@FAR=1E-6 (MS1MV2)TAR: 85.30 -> 86.60Improved
use DPAP instead of RandAugment (ablation)ViT-S · IJB-C TAR@FAR=1E-4 (MS1MV2)TAR: 96.14 -> 96.30Improved
use EHSM instead of Focal loss (ablation)ViT-S · IJB-C TAR@FAR=1E-4 (MS1MV2)TAR: 96.11 -> 96.22Improved

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