Small-data image classification via drop-in variational autoencoder

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F25%3A00636756" target="_blank" >RIV/67985556:_____/25:00636756 - isvavai.cz</a>

Result on the web

<a href="https://link.springer.com/article/10.1007/s11760-025-04376-1" target="_blank" >https://link.springer.com/article/10.1007/s11760-025-04376-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11760-025-04376-1" target="_blank" >10.1007/s11760-025-04376-1</a>

Result language

angličtina

Original language name

Small-data image classification via drop-in variational autoencoder

Original language description

It is unclear whether generative approaches can achieve state-of-the-art performance with supervised classification in highdimensional feature spaces and extremely small datasets. In this paper, we propose a drop-in variational autoencoder (VAE) for the task of supervised learning using an extremely small train set (i.e., n = 1,..,5 images per class). Drop-in classifiers form a usual alternative when traditional approaches to Few-Shot Learning cannot be used. The classification will be defined as a posterior probability density function and approximated by the variational principle. We perform experiments on a large variety of deep feature representations extracted from different layers of popular convolutional neural network (CNN) architectures. We also benchmark with modern classifiers, including Neural Tangent Kernel (NTK), Support Vector Machine (SVM) with NTK kernel and Neural Network Gaussian Process (NNGP). Results obtained indicate that the drop-in VAE classifier outperforms all the compared classifiers in the extremely small data regime.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

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

Name of the periodical

Signal Image and Video Processing

ISSN

1863-1703

e-ISSN

1863-1711

Volume of the periodical

19

Issue of the periodical within the volume

1

Country of publishing house

CH - SWITZERLAND

Number of pages

9

Pages from-to

766

UT code for WoS article

001512352600001

EID of the result in the Scopus database

2-s2.0-105008514329