AI Paper Atlas

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

Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning

Denis Huseljic, Marek Herde, Lukas Rauch, Paul Hahn, Bernhard Sick

CVPR 2026 · 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
increase filtering rounds R from 1 to 7 (ablation)progressive filtering + random sampling · CIFAR-10AULC improvement [%]: 3.02 -> 3.81Improved
increase filtering rounds R from 1 to 9 (ablation)progressive filtering + random sampling · SnacksAULC improvement [%]: 6.91 -> 8.43Improved
increase R from 7 to 9 (ablation)progressive filtering · CIFAR-10AULC improvement [%]: 3.81 -> 3.78No clear effect
use very low sampling ratio alpha=0.2 instead of 0.3 (ablation)progressive filtering · CIFAR-10AULC improvement [%]: 3.89 -> 3.33Hurt
vary alpha between 0.3 and 0.9 (ablation)progressive filtering · SnacksAULC improvement [%]: 7.60 -> 8.40No clear effect
increase batches per strategy J from 1 to 20 (ablation)progressive filtering · CIFAR-10AULC improvement [%]: 3.57 -> 3.93Improved
increase J from 1 to 20 (ablation)progressive filtering · SnacksAULC improvement [%]: 7.88 -> 7.69No clear effect
apply progressive filtering as preprocessing to individual AL strategiesrandom sampling, Margin, BAIT, AlfaMix, UHerding · CIFAR-100 (DINOv2/DINOv3)AULC improvement [%]: +0.7% to +5.4%Improved
apply progressive filtering before BAITBAIT · CIFAR-100 (DINOv3)AULC improvement [%]: +4.9%Improved
apply progressive filtering before CoresetCoreset · ESC50 (EAT base)accuracy: up to 10%Improved
use FIR or expected-error batch ranking instead of coverage-based second stage (ablation)REFINE · Dopanim and CIFAR-100 (DINOv2)relative accuracyNo clear effect
increase batch size b from 10 to 100 at fixed budget (ablation)REFINE · CIFAR-100 (DINOv2)accuracyImproved

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