AI Paper Atlas

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

TransFace++: Rethinking the Face Recognition Paradigm With a Focus on Accuracy, Efficiency, and Security

Jun Dan, Yang Liu, Baigui Sun, Jiankang Deng, Shan Luo

TPAMI 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 13 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 TransFace (DPAP and EHSM) to ViT-BViT-B · IJB-C TAR@FAR=1e-5 (WebFace42M, RGB)verification accuracy (%): 96.07 -> 97.25Improved
add TransFace to ViT-LViT-L · IJB-C TAR@FAR=1e-4 (WebFace42M, RGB)verification accuracy (%): 97.65 -> 98.16Improved
add TransFace to ViT-S on small MS1MV2ViT-S · IJB-C TAR@FAR=1e-4 (MS1MV2, RGB)verification accuracy (%): 95.89 -> 96.45Improved
train TransFace on limited-size MS1MV2 versus large setsTransFace · MS1MV2 IJB-B/IJB-Cverification accuracy (%)Mixed
add TIBC and SICA to ViT-L on PNG bytesViT-L · IJB-C TAR@FAR=1e-4 (MS1MV2, PNG bytes)verification accuracy (%): 93.75 -> 96.37Improved
add TIBC and SICA to ViT-L on TIFF bytesViT-L · IJB-C TAR@FAR=1e-4 (MS1MV2, TIFF bytes)verification accuracy (%): 95.25 -> 96.85Improved
feed TIFF bytes with TransFace++-L instead of RGB ViT-LTransFace++-L · IJB-C TAR@FAR=1e-4 (MS1MV2)verification accuracy (%): +0.61%Improved
use PNG instead of TIFF encoding for bytes inputTransFace++-L · IJB-C TAR@FAR=1e-4 (MS1MV2)verification accuracy (%): 96.85 -> 96.37Hurt
randomly shuffle byte order during training (ablation)ViT-S TIFF bytes · IJB-C TAR@FAR=1e-4 (MS1MV2)verification accuracy (%): 94.74 -> 74.25Hurt
apply strided sampling to bytes (ablation)ViT-S TIFF bytes · IJB-C TAR@FAR=1e-4 (MS1MV2)verification accuracy (%): 94.74 -> 79.56Hurt
apply window shuffle to bytes (ablation)ViT-S TIFF bytes · IJB-C TAR@FAR=1e-4 (MS1MV2)verification accuracy (%): 94.74 -> 83.30Hurt
reverse byte order (ablation)ViT-S TIFF bytes · IJB-C TAR@FAR=1e-4 (MS1MV2)verification accuracy (%): 94.74 -> 93.76Mixed

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