AI Paper Atlas

Research map / Detection and segmentation / CNN features

Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation Costs

Lile Cai, Xun Xu, Jun Hao Liew, Chuan Sheng Foo

CVPR 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 59 citations (OpenAlex)

Check 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
Use superpixels with dominant labeling instead of rectangles with precise polygon labelingRegion-based active learning · Cityscapesannotation cost to obtain 95% accuracy (% of total clicks): 15.70% -> 9.81%Improved
Add class-balanced selection to superpixel dominant-label samplingSuperpixel-based active learning · Cityscapesannotation cost to obtain 95% accuracy (% of total clicks): 9.81% -> 7.85%Improved
Measure annotation cost in clicks rather than labeled-pixel percentageSuperpixel-based versus rectangle-based active learning · CityscapesmIoUMixed
Use dominant labeling rather than precise polygon labeling (ablation)Rectangular-region active learning · CityscapesmIoUHurt
Use class-balanced selection rather than uncertainty selection (ablation)Superpixel-based active learning · PASCAL VOC 2012mIoUNo clear effect
Use smaller regions rather than larger regions (ablation)Superpixel and rectangle region-based active learning · CityscapesmIoUImproved
Increase superpixel region size beyond 128 × 128 (ablation)Superpixel-based active learning · CityscapesmIoUHurt
Add class-balanced sampling (ablation)Superpixel-based active learning · Cityscapesclass-wise IoUMixed
Use uncertainty selection instead of random selection (ablation)Rectangle+polygon active learning · PASCAL VOC 2012mIoUHurt

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