atlas

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

Active Sampling for Open-Set Classification without Initial Annotation

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 20 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 diversity term to active sampling (ablation)ASOCIA · ExtendedYaleBF1-total: 0.964 -> 0.966Helped
add diversity term to active sampling (ablation)ASOCIA · Coil20F1-total: 0.927 -> 0.982Helped
add diversity term to active sampling (ablation)ASOCIA · Fashion-MNISTF1-total: 0.539 -> 0.571Helped
add diversity term to active sampling (ablation)ASOCIA · Fashion-MNISTAccuracy-known: 0.818 -> 0.810Hurt
add diversity term to active sampling (ablation)ASOCIA · ExtendedYaleB multi-stage, stage threeF1-Measure: 0.968 -> 0.964No clear effect
ASOCIA vs ASG adversarial boundary methodASOCIA · Fashion-MNISTF1-total: 0.322 -> 0.571Helped
increase affiliation-matrix budget from 15 to 90 (ablation)ASOCIA · ExtendedYaleB, Fashion-MNIST, Coil20Accuracy-known / F1Helped

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