AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Scaling Up Instance Annotation via Label Propagation

Dim P. Papadopoulos, Ethan Weber, Antonio Torralba

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 11 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
cluster on mask attention features combined with mask score instead of other feature types (ablation)hierarchical clustering · ADE20K simulatedannotations vs clustersImproved
use heuristics-only search with mask score instead of BFS or DFS or universal thresholding (ablation)tree search · ADE20K simulatedannotations vs clustersImproved
set K_pa high (very high values) when selecting clusters (ablation)active cluster selection · ADE20K simulatednumber of good annotationsHurt
use low K_pa values rather than K_pa=0.7 (ablation)active cluster selection · ADE20K simulatedannotation performanceNo clear effect
increase initial training set size from 500 to 10,000 images (ablation)label propagation · ADE20K simulatedannotation quantityImproved
use label propagation pipeline instead of confidence-score filteringPointRend predictions · ADE20K simulatedannotations at matched quality: 67 -> 15,628Improved
verify all masks per cluster (N_s = infinity) instead of N_s = 15 (ablation)label propagation · Large-scale simulationSQ: 0.85 -> 0.89Improved
train detector on propagated labels plus initial set instead of initial set onlyPointRend · ADE20K valAP: 8.1 -> 12.7Improved
use propagated labels instead of spending same 73 h on manual annotationPointRend · ADE20K valAP: 9.6 -> 12.7Improved
apply hyperparameters tuned on ADE20K to COCO and OpenImages without retuninglabel propagation · COCO and OpenImagesannotation gainNo clear effect

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