AI Paper Atlas

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

MSML: Enhancing Occlusion-Robustness by Multi-Scale Segmentation-Based Mask Learning for Face Recognition

Ge Yuan, Huicheng Zheng, Jiayu Dong

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 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 multi-scale segmentation-based masking to ArcFace-18ArcFace-18 · MFVverification accuracy (%): 95.40 -> 98.90Improved
Add multi-scale segmentation-based masking to ArcFace-18ArcFace-18 · MFVTAR(@FAR=1e-3) (%): 81.10 -> 91.93Improved
Add multi-scale segmentation-based masking to ArcFace-18ArcFace-18 · MF1occidentification accuracy (%): 64.50 -> 68.33Improved
Add multi-scale segmentation-based masking to LightCNN-29LightCNN-29 · AR Protocol 2, Scarfidentification accuracy (%): 96.76 -> 99.37Improved
Use a soft sigmoid mask instead of binarization (ablation)MSML v1 configuration on L29 · LFW block occlusion 1%-40%verification accuracy (%): 93.00 -> 94.43Improved
Use concatenated facial features and segmentation representations to generate masks (ablation)MSML on L29 · LFW block occlusion 1%-40%verification accuracy (%): 94.43 -> 95.27Improved
Add two ResBlocks to the mask operator (ablation)MSML on L29 · LFW block occlusion 1%-40%verification accuracy (%): 95.87 -> 96.30Improved
Remove the layer 1 masking operator (ablation)MSML on L29 · LFW block occlusion 1%-40%verification accuracy (%): 96.30 -> 91.73Hurt
Remove the layer 2 masking operator (ablation)MSML on L29 · LFW block occlusion 1%-40%verification accuracy (%): 96.30 -> 95.40Hurt
Remove the layer 3 masking operator (ablation)MSML on L29 · LFW block occlusion 1%-40%verification accuracy (%): 96.30 -> 95.35Hurt
Remove the layer 4 masking operator (ablation)MSML on L29 · LFW block occlusion 1%-40%verification accuracy (%): 96.30 -> 90.27Hurt
Replace the OSB ResNet-18 encoder with ResNet-34 (ablation)MSML with ArcFace-18 · MFVverification accuracy (%): 98.90 -> 98.43Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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