AI Paper Atlas

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

To Label or Not to Label: PALM - A Predictive Model for Evaluating Sample Efficiency in Active Learning Models

Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 1 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
add pretrained SSL embeddings to Margin samplingMargin sampling · CIFAR-10delta: 0.094 -> 0.535Improved
add pretrained SSL embeddings to Random samplingRandom sampling · CIFAR-100delta: 0.048 -> 0.318Improved
add pretrained SSL embeddings to Margin samplingMargin sampling · CIFAR-100alpha: 10.643 -> 0.068Improved
use embeddings with Random sampling versus Entropy sampling without embeddingsActive learning · CIFAR-10delta: 0.066 -> 0.536Improved
fit PALM on about 1,000 labeled samples instead of full curvePALM · CIFAR-10curve prediction: 1,000 samples (2% of the dataset)Improved
fit PALM on about 5,000 labeled samplesPALM · CIFAR-100curve prediction: 5,000 samples (10% of the dataset)Improved
use MoCov3 embeddings instead of BYOL/MoCov2+Active learning · ImageNet-200A_max and deltaImproved
use BYOL embeddingsActive learning · ImageNet subsetsdeltaHurt
enlarge the number of fit points for BYOLPALM · ImageNet subsetscurve fitMixed

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