AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

Xuanyi Dong, Yi Yang

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 84 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 the HG student and student interaction to a single CPM student (10% labels) (ablation)TS3 · 300-W Full testNME: 8.28 -> 5.64Improved
add the CPM student and student interaction to a single HG student (10% labels) (ablation)TS3 · 300-W Full testNME: 6.25 -> 5.64Improved
add the HG student to a single CPM student (20% labels) (ablation)TS3 · 300-W Full testNME: 6.68 -> 5.03Improved
add the CPM student to a single HG student (20% labels) (ablation)TS3 · 300-W Full testNME: 6.68 -> 5.03Improved
add the HG student to CPM on challenging subset (10% labels) (ablation)TS3 · 300-W ChallengingNME: 14.69 -> 9.26Improved
add the learned teacher to select pseudo labels, versus SPL and SPaCo selection (ablation)TS3 · 300-W Full test (10% labels)NMEImproved
raise label ratio from 10% to 20%TS3 · 300-W Full testNME: 5.64 -> 5.03Improved
use TS3 instead of RCN+ with 10% labelsTS3 · 300-W Full testNME: 6.32 -> 5.64Improved
use TS3 instead of RCN+ with 20% labelsTS3 · 300-W Full testNME: 5.88 -> 5.03Improved
add unlabeled AFLW training data to 100% labeled 300-WTS3 · 300-W Full testNME: 3.78 -> 3.49Improved
increase label ratio from 5% to 20%TS3 · AFLW-FullNME: 2.19 -> 1.99Improved
add unlabeled 300-VW videos with only 300-W labels, versus fully labeled baselinesTS3 · 300-VW category CAUC@0.08: 59.39 -> 59.65Improved

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