AI Paper Atlas

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

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

Guy Hacohen, Avihu Dekel, Daphna Weinshall

ICML 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 33 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
select diverse typical examples with TypiClust instead of random selectionFlexMatch · CIFAR-10, 10 labeled examplesaccuracy: 39.4%Improved
use TypiClust rather than random, balanced or unbalanced selectionFlexMatch · CIFAR-100, 300 labeled examplesaccuracyImproved
use TypiClust rather than random, balanced or unbalanced selectionFlexMatch · TinyImageNet, 1000 labeled examplesaccuracyImproved
use TypiClust instead of baseline active-learning strategiesfully supervised image classification · CIFAR-10, CIFAR-100, and ImageNet-100, low budgetaccuracyImproved
use TypiClust instead of baseline active-learning strategieslinear classifier on self-supervised embeddings · CIFAR-10, CIFAR-100, and ImageNet-100, low budgetaccuracyImproved
use random initial pool selection (ablation)TypiClust · fully supervised low-budget experimentsaccuracyHurt
select a random example from each cluster instead of the most typical example (ablation)TypiClust · CIFAR-10, low budgetaccuracyHurt
select the most atypical example in each cluster instead of the most typical (ablation)TypiClust · CIFAR-10, low budgetaccuracyHurt
remove clustering and select typical samples greedily (ablation)TypiClust · CIFAR-10, low budgetaccuracyHurt
use oracle-estimated uncertainty to query examples (ablation)active learning on CIFAR-10 · CIFAR-10, low budgetaccuracyHurt
prefer typical examples rather than uncertain examplesactive learning · low-budget regimegeneralization errorImproved
prefer atypical or confusing examples rather than typical examplesactive learning · high-budget regimegeneralization errorImproved

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