AI Paper Atlas

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

Active Decision Boundary Annotation With Deep Generative Models

Miriam Huijser, Jan C. van Gemert

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 40 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
annotate decision boundary points instead of only sample labelsuncertainty sampling · SVHN 0 vs. 8AULC: 118.7 -> 124.3Improved
annotate decision boundary points instead of only sample labelsuncertainty-dense sampling · Shoe-BagAULC: 112.0 -> 135.2Improved
annotate decision boundary points instead of only sample labels5 cluster centroid · SVHN 0 vs. 8AULC: 98.0 -> 106.3Improved
annotate decision boundary points instead of only sample labelsrandom sampling · MNIST 0 vs. 8AULC: 142.2 -> 145.1Improved
use uncertainty sampling rather than other query strategies (ablation)active learning · MNIST 0 vs. 8AULC: 135.6 -> 144.0Improved
add Gaussian noise (sigma 5 images) to boundary annotations (ablation)boundary annotation · SVHN 0 vs. 8AULC: 124.0 -> 113.6Hurt
add Gaussian noise (sigma 1 to 4 images) to boundary annotations (ablation)boundary annotation · MNIST 0 vs. 8AULC: 146.0 -> 144.2Hurt
use human oracle instead of SVM oracle for boundary annotation (ablation)boundary annotation · MNIST 0 vs. 8 (10 queries)AULC: 9.1 -> 8.8Hurt
annotate decision boundary with human oracle instead of sample labelsactive learning · SVHN 0 vs. 8 (10 queries)AULC: 5.7 -> 5.8No clear effect
annotate decision boundary instead of samples, averaged over all class pairsactive learning · SVHN (all class pairs)AULC: 127.8 -> 130.9Improved
use a lower quality generative model (Shoe-Bag embedding) (ablation)human annotation consistency · Shoe-Baglines without change: 5 of 10 lines without changeHurt

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