Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00383742" target="_blank" >RIV/68407700:21230/25:00383742 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/WACV61041.2025.00190" target="_blank" >https://doi.org/10.1109/WACV61041.2025.00190</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV61041.2025.00190" target="_blank" >10.1109/WACV61041.2025.00190</a>

Result language

angličtina

Original language name

Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization

Original language description

Single-source domain generalization attempts to learn a model on a source domain and deploy it to unseen target domains. Limiting access only to source domain data imposes two key challenges - how to train a model that can generalize and how to verify that it does. The standard practice of validation on the training distribution does not accurately reflect the model's generalization ability, while validation on the test distribution is a malpractice to avoid. In this work, we construct an independent validation set by transforming source domain images with a comprehensive list of augmentations, covering a broad spectrum of potential distribution shifts in target domains. We demonstrate a high correlation between validation and test performance for multiple methods and across various datasets. The proposed validation achieves a relative accuracy improvement over the standard validation equal to 15.4% or 1.6% when used for method selection or learning rate tuning, respectively. Furthermore, we introduce a novel family of methods that increase the shape bias through enhanced edge maps. To benefit from the augmentations during training and preserve the independence of the validation set, a k-fold validation process is designed to separate the augmentation types used in training and validation. The method that achieves the best performance on the augmented validation is selected from the proposed family. It achieves state-of-the-art performance on various standard benchmarks. Code at: https://github.com/NikosEfth/crafting-shifts

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

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

Publication year

2025

Confidentiality

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

Article name in the collection

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

ISBN

979-8-3315-1084-8

ISSN

2472-6737

e-ISSN

2642-9381

Number of pages

10

Pages from-to

1883-1892

Publisher name

IEEE

Place of publication

Piscataway

Event location

Tucson

Event date

Feb 28, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001481328900180