AI Paper Atlas

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

Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network

Lingxue Song, Dihong Gong, Zhifeng Li, Changsong Liu, Wei Liu

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 288 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 differential input and pairwise loss to mask learning (ablation)PDSN · AR sunglasses (Protocol 2)rank-1 identification accuracy (%): 95.97 -> 98.19Improved
add differential input and pairwise loss to mask learning (ablation)PDSN · AR scarf (Protocol 2)rank-1 identification accuracy (%): 97.92 -> 98.33Improved
add differential input and pairwise loss to mask learning (ablation)PDSN · occluded Facescrub MF1occaccuracy (%): 54.80 -> 56.34Improved
binarize mask instead of using soft weights (ablation)FDM · AR sunglasses (Protocol 2)rank-1 identification accuracy (%): 96.67 -> 98.19Improved
binarize mask instead of using soft weights (ablation)FDM · AR scarf (Protocol 2)rank-1 identification accuracy (%): 97.22 -> 98.33Improved
zero low mask values but keep the rest unchanged (Soft+Binary) instead of fully binary (ablation)FDM · AR scarf (Protocol 2)rank-1 identification accuracy (%): 98.33 -> 99.03No clear effect
increase discarding threshold tau from 0 to 0.25 (ablation)FDM · AR sunglasses+scarfrank-1 identification accuracy (%): 95.84 -> 98.26Improved
increase discarding threshold tau from 0.25 to 0.45 (ablation)FDM · AR sunglasses+scarfrank-1 identification accuracy (%): 98.26 -> 97.92Hurt
fine-tune trunk CNN on synthetic occluded faces (Baseline)Trunk CNN · LFWverification accuracy (%): 99.20 -> 98.68Hurt
fine-tune trunk CNN on synthetic occluded faces (Baseline)Trunk CNN · MegaFace Challenge 1 (small)rank-1 identification accuracy (%): 74.40 -> 68.81Hurt
add PDSN feature discarding masks to trunk CNNTrunk CNN · occluded Facescrub MF1occaccuracy (%): 51.86 -> 56.34Improved
add PDSN feature discarding masks to trunk CNNTrunk CNN · AR sunglasses (Protocol 2)rank-1 identification accuracy (%): 95.14 -> 98.19Improved

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