AI Paper Atlas

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

End2End Occluded Face Recognition by Masking Corrupted Features

Haibo Qiu, Dihong Gong, Zhifeng Li, Wei Liu, Dacheng Tao

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 132 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 occluded data augmentation (ablation)Baseline · Occ-LFW-2.0verification accuracy (%): 82.05 -> 94.10Improved
add occluded data augmentation (ablation)Baseline · MF1identification accuracy (%): 73.64 -> 72.50Hurt
add Mask Decoder (ablation)Baseline-Aug · MF1identification accuracy (%): 72.50 -> 74.17Improved
add Occlusion Pattern Predictor (ablation)Baseline-MD · Occ-MF1-AVGidentification accuracy (%): 68.19 -> 69.85Improved
add Occlusion Pattern Predictor (ablation)Baseline-MD · MF1identification accuracy (%): 74.17 -> 75.27Improved
use FROM masks instead of no masksBaseline · Occ-MF1-1.0identification accuracy (%): 32.00 -> 60.84Improved
increase grid K from 3 to 5 (ablation)FROM · Occ-MF1 averageidentification accuracy (%): 43.81 -> 44.83Improved
increase grid K from 5 to 6 (ablation)FROM · Occ-MF1 averageidentification accuracy (%): 44.83 -> 44.91No clear effect
add pattern prediction loss (lambda 0 to 1.0) (ablation)FROM · Occ-MF1 averageidentification accuracy (%): 43.48 -> 44.83Improved
lambda 0.5 instead of 1.0 (ablation)FROM · Occ-MF1 averageidentification accuracy (%): 45.00 vs 44.83No clear effect
apply masks on conv features instead of fc features (ablation)FROM · Occ-MF1 averageidentification accuracy (%): 44.05 -> 44.83Improved
use 3D masks instead of 2D masks (ablation)FROM · Occ-MF1 averageidentification accuracy (%): 44.35 -> 44.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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