AI Paper Atlas

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

Active Self-Paced Learning for Cost-Effective and Progressive Face Identification

Liang Lin, Keze Wang, Deyu Meng, Wangmeng Zuo, Lei Zhang

TPAMI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 161 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
combine active learning with self-paced learning (ASPL) instead of AL_RAND/CCAL/CPALincremental face identification · CACDannotation amount to match accuracy: 81% -> 40%Improved
combine active learning with self-paced learning (ASPL) instead of AL_RAND/CCAL/CPALincremental face identification · CASIA-WebFace-Subannotation amount to match accuracy: 65% -> 45%Improved
add CNN fine-tuning (ablation)ASPL · CASIA-WebFace-Subrecognition accuracyImproved
add self-paced learning (SPL) component (ablation)ASPL · CASIA-WebFace-Subrecognition accuracyImproved
add active learning (AL) component (ablation)ASPL · CASIA-WebFace-Subrecognition accuracyImproved
add CNN fine-tuning (ablation)ASPL · CASIA-WebFace-Sub, iteration 5pseudo-label error rate: 8.2% -> 4.5%Improved
add CNN fine-tuning (ablation)ASPL · CASIA-WebFace-Sub, iteration 25pseudo-label error rate: 4.9% -> 3.3%Improved
add active learning to self-paced learning (ablation)ASPL · CASIA-WebFace-Sub (20 individuals)sensitivity to initial samplesImproved
handle unseen new classes incrementally instead of giving all classes at start (ablation)ASPL · CASIA-WebFace-Sub, 600 classesaccuracy: 81.0% -> 81.6%No clear effect
handle unseen new classes incrementally instead of giving all classes at start (ablation)ASPL · CASIA-WebFace-Sub, 925 classesaccuracy: 76.0% -> 76.0%No clear effect
add annotated-sample verification step (ablation)ASPL · CASIA-WebFace-Sub with noisy labelsrecovery speed from noiseImproved
add noisy initial annotations (10-50%)ASPL · CASIA-WebFace-Subtest accuracyHurt

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