AI Paper Atlas

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

Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation

Chen-Chen Zong, Ye-Wen Wang, Kun-Peng Ning, Hai-Bo Ye, Sheng-Jun Huang

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 5 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
use negative-head uncertainty instead of positive-head uncertainty alone (ablation)BUAL (B-LC) · CIFAR-10 (openness 0.6)final accuracy (%): 87.5 -> 89.4Improved
combine positive and negative uncertainty (no balancing factors) (ablation)BUAL (B-LC) · CIFAR-10 (openness 0.6)final accuracy (%): 89.4 -> 90.8Improved
add global balancing factor r (ablation)BUAL (B-LC) · CIFAR-10 (openness 0.6)final accuracy (%): 90.8 -> 91.3Improved
add local balancing factor f_aux (ablation)BUAL (B-LC) · CIFAR-10 (openness 0.6)final accuracy (%): 91.3 -> 92.5Improved
add balancing factors and negative head on CIFAR-100 (ablation)BUAL (B-LC) · CIFAR-100 (openness 0.6)final accuracy (%): 63.5 -> 62.4 (w/o w) -> 67.5Mixed
negative learning fine-tuning + bidirectional uncertainty vs Margin samplingMargin · CIFAR-10 (openness 0.6)final accuracy (%): 89.0 -> 92.6Improved
open-set annotation methods LfOSA/CCAL when openness is lowLfOSA · CIFAR-10 (openness 0.2)final accuracy (%): 83.3 -> 73.7Hurt
diversity-based selection (Coreset, BADGE) at high opennessCoreset · CIFAR-10 (openness 0.4)final accuracy (%): 82.5 -> 81.8No 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