Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F21%3A00356449" target="_blank" >RIV/68407700:21240/21:00356449 - isvavai.cz</a>

Výsledek na webu

<a href="https://proceedings.mlr.press/v140/chobola21a.html" target="_blank" >https://proceedings.mlr.press/v140/chobola21a.html</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

Popis výsledku v původním jazyce

The MetaDL Challenge 2020 focused on image classification tasks in few-shot settings. This paper describes second best submission in the competition. Our meta learning approach modifies the distribution of classes in a latent space produced by a backbone network for each class in order to better follow the Gaussian distribution. After this operation which we call Latent Space Transform algorithm, centers of classes are further aligned in an iterative fashion of the Expectation Maximisation algorithm to utilize information in unlabeled data that are often provided on top of few labelled instances. For this task, we utilize optimal transport mapping using the Sinkhorn algorithm. Our experiments show that this approach outperforms previous works as well as other variants of the algorithm, using K-Nearest Neighbour algorithm, Gaussian Mixture Models, etc.

Název v anglickém jazyce

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

Popis výsledku anglicky

The MetaDL Challenge 2020 focused on image classification tasks in few-shot settings. This paper describes second best submission in the competition. Our meta learning approach modifies the distribution of classes in a latent space produced by a backbone network for each class in order to better follow the Gaussian distribution. After this operation which we call Latent Space Transform algorithm, centers of classes are further aligned in an iterative fashion of the Expectation Maximisation algorithm to utilize information in unlabeled data that are often provided on top of few labelled instances. For this task, we utilize optimal transport mapping using the Sinkhorn algorithm. Our experiments show that this approach outperforms previous works as well as other variants of the algorithm, using K-Nearest Neighbour algorithm, Gaussian Mixture Models, etc.

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/GA18-18080S" target="_blank" >GA18-18080S: Objevování znalostí v datech o aktivitě člověka založené na fúzi</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

AAAI Workshop on Meta-Learning and MetaDL Challenge

ISBN

—

ISSN

2640-3498

e-ISSN

2640-3498

Počet stran výsledku

9

Strana od-do

29-37

Název nakladatele

Proceedings of Machine Learning Research

Místo vydání

—

Místo konání akce

Virtuální

Datum konání akce

8. 2. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—