The Hitchhiker's Guide to Prior-Shift Adaptation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00363002" target="_blank" >RIV/68407700:21230/22:00363002 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/WACV51458.2022.00209" target="_blank" >https://doi.org/10.1109/WACV51458.2022.00209</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV51458.2022.00209" target="_blank" >10.1109/WACV51458.2022.00209</a>

Jazyk výsledku

angličtina

Název v původním jazyce

The Hitchhiker's Guide to Prior-Shift Adaptation

Popis výsledku v původním jazyce

In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance. This paper analyzes methods for adaptation of probabilistic classifiers to new priors and for estimating new priors on an unlabeled test set. We propose a novel method to address a known issue of prior estimation methods based on confusion matrices, where inconsistent estimates of decision probabilities and confusion matrices lead to negative values in the estimated priors. Experiments on fine-grained image classification datasets provide insight into the best practice of prior shift estimation and classifier adaptation, and show that the proposed method achieves state-of-the-art results in prior adaptation. Applying the best practice to two tasks with naturally imbalanced priors, learning from web-crawled images and plant species classification, increased the recognition accuracy by 1.1% and 3.4% respectively.

Název v anglickém jazyce

The Hitchhiker's Guide to Prior-Shift Adaptation

Popis výsledku anglicky

In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance. This paper analyzes methods for adaptation of probabilistic classifiers to new priors and for estimating new priors on an unlabeled test set. We propose a novel method to address a known issue of prior estimation methods based on confusion matrices, where inconsistent estimates of decision probabilities and confusion matrices lead to negative values in the estimated priors. Experiments on fine-grained image classification datasets provide insight into the best practice of prior shift estimation and classifier adaptation, and show that the proposed method achieves state-of-the-art results in prior adaptation. Applying the best practice to two tasks with naturally imbalanced priors, learning from web-crawled images and plant species classification, increased the recognition accuracy by 1.1% and 3.4% respectively.

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

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022

ISBN

978-1-6654-0915-5

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

9

Strana od-do

2031-2039

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Waikoloa

Datum konání akce

3. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000800471202010