Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376838" target="_blank" >RIV/68407700:21230/24:00376838 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/WACV57701.2024.00033" target="_blank" >https://doi.org/10.1109/WACV57701.2024.00033</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV57701.2024.00033" target="_blank" >10.1109/WACV57701.2024.00033</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning

Popis výsledku v původním jazyce

Deep active learning in the presence of outlier examples poses a realistic yet challenging scenario. Acquiring unlabeled data for annotation requires a delicate balance between avoiding outliers to conserve the annotation budget and prioritizing useful inlier examples for effective training. In this work, we present an approach that leverages three highly synergistic components, which are identified as key ingredients: joint classifier training with inliers and outliers, semi-supervised learning through pseudo-labeling, and model ensembling. Our work demonstrates that ensembling significantly enhances the accuracy of pseudolabeling and improves the quality of data acquisition. By enabling semi-supervision through the joint training process, where outliers are properly handled, we observe a substantial boost in classifier accuracy through the use of all available unlabeled examples. Notably, we reveal that the integration of joint training renders explicit outlier detection unnecessary; a conventional component for acquisition in prior work. The three key components align seamlessly with numerous existing approaches. Through empirical evaluations, we showcase that their combined use leads to a performance increase. Remarkably, despite its simplicity, our proposed approach outperforms all other methods in terms of performance. Code: https://github.com/vladan-stojnic/active-outliers

Název v anglickém jazyce

Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning

Popis výsledku anglicky

Deep active learning in the presence of outlier examples poses a realistic yet challenging scenario. Acquiring unlabeled data for annotation requires a delicate balance between avoiding outliers to conserve the annotation budget and prioritizing useful inlier examples for effective training. In this work, we present an approach that leverages three highly synergistic components, which are identified as key ingredients: joint classifier training with inliers and outliers, semi-supervised learning through pseudo-labeling, and model ensembling. Our work demonstrates that ensembling significantly enhances the accuracy of pseudolabeling and improves the quality of data acquisition. By enabling semi-supervision through the joint training process, where outliers are properly handled, we observe a substantial boost in classifier accuracy through the use of all available unlabeled examples. Notably, we reveal that the integration of joint training renders explicit outlier detection unnecessary; a conventional component for acquisition in prior work. The three key components align seamlessly with numerous existing approaches. Through empirical evaluations, we showcase that their combined use leads to a performance increase. Remarkably, despite its simplicity, our proposed approach outperforms all other methods in terms of performance. Code: https://github.com/vladan-stojnic/active-outliers

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

ISBN

979-8-3503-1892-0

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

10

Strana od-do

259-268

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Waikoloa, HI, USA

Datum konání akce

4. 1. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001222964600026