AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

BAL: Balancing Diversity and Novelty for Active Learning

Jingyao Li, Pengguang Chen, Shaozuo Yu, Shu Liu, Jiaya Jia

TPAMI 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 26 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 rotation-angle pretext instead of SimCLR (ablation)BAL · CIFAR-10 (10% labeled)accuracy (%): 50.8 -> 68.7Improved
use rotation-angle labels instead of image labels (ablation)BAL · CIFAR-10 (10% labeled)accuracy (%): 65.0 -> 68.7Improved
use CDD instead of distance to nearest cluster center (ablation)BAL · CIFAR-10 (10% labeled)accuracy (%): 66.6 -> 68.7Improved
sort CDD ascending instead of descending (ablation)BAL · CIFAR-10 (10% labeled)accuracy (%): 57.5 -> 70.5Improved
use confidence sampler instead of entropy (ablation)BAL · CIFAR-10 (10% labeled)accuracy (%): 53.4 -> 68.7Improved
use confidence sampler instead of random (ablation)BAL · CIFAR-10 (10% labeled)accuracy (%): 68.2 -> 68.7Improved
use adaptive sub-pools instead of uniform sub-pools (ablation)BAL · Caltech-101 (45% labeled)accuracy (%): 75.0 -> 76.4Improved
use CDD instead of pretext task loss as indicator (ablation)PT4AL · CIFAR-10accuracy (%): +1.36%Improved
use BAL instead of PT4AL under large budget (80% labeled)BAL · Caltech-101 (80% labeled)accuracy (%): 82.6 -> 92.8Improved
use BAL instead of PT4AL under large budget (80% labeled)BAL · CIFAR-10 (80% labeled, from scratch)accuracy (%): 91.4 -> 85.0Hurt
use BAL instead of ActiveFT under small budget (4% labeled)BAL · SVHN (4% labeled)accuracy (%): 55.3 -> 81.3Improved
use BAL instead of entropy under small budget (4% labeled)BAL · CIFAR-10 (4% labeled)accuracy (%): 25.7 -> 36.7Improved

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