Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification
In developing a few-shot classification model using deep networks, the limited number of samples in each class causes difficulty in utilizing statistical characteristics of the class distributions. In this paper, we propose a method to treat this difficulty by combining a probabilistic similarity ba...
Guardado en:
Autores principales: | , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/7f50fb27736747cb881c6b3232758cdb |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:7f50fb27736747cb881c6b3232758cdb |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:7f50fb27736747cb881c6b3232758cdb2021-11-25T16:42:18ZEffect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification10.3390/app1122109772076-3417https://doaj.org/article/7f50fb27736747cb881c6b3232758cdb2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10977https://doaj.org/toc/2076-3417In developing a few-shot classification model using deep networks, the limited number of samples in each class causes difficulty in utilizing statistical characteristics of the class distributions. In this paper, we propose a method to treat this difficulty by combining a probabilistic similarity based on intra-class statistics with a metric-based few-shot classification model. Noting that the probabilistic similarity estimated from intra-class statistics and the classifier of conventional few-shot classification models have a common assumption on the class distributions, we propose to apply the probabilistic similarity to obtain loss value for episodic learning of embedding network as well as to classify unseen test data. By defining the probabilistic similarity as the probability density of difference vectors between two samples with the same class label, it is possible to obtain a more reliable estimate of the similarity especially for the case of large number of classes. Through experiments on various benchmark data, we confirm that the probabilistic similarity can improve the classification performance, especially when the number of classes is large.Youngjae LeeHyeyoung ParkMDPI AGarticlefew-shot classificationmetric-learningprobabilistic similarityintra-class statisticsTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10977, p 10977 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
few-shot classification metric-learning probabilistic similarity intra-class statistics Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 |
spellingShingle |
few-shot classification metric-learning probabilistic similarity intra-class statistics Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Youngjae Lee Hyeyoung Park Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification |
description |
In developing a few-shot classification model using deep networks, the limited number of samples in each class causes difficulty in utilizing statistical characteristics of the class distributions. In this paper, we propose a method to treat this difficulty by combining a probabilistic similarity based on intra-class statistics with a metric-based few-shot classification model. Noting that the probabilistic similarity estimated from intra-class statistics and the classifier of conventional few-shot classification models have a common assumption on the class distributions, we propose to apply the probabilistic similarity to obtain loss value for episodic learning of embedding network as well as to classify unseen test data. By defining the probabilistic similarity as the probability density of difference vectors between two samples with the same class label, it is possible to obtain a more reliable estimate of the similarity especially for the case of large number of classes. Through experiments on various benchmark data, we confirm that the probabilistic similarity can improve the classification performance, especially when the number of classes is large. |
format |
article |
author |
Youngjae Lee Hyeyoung Park |
author_facet |
Youngjae Lee Hyeyoung Park |
author_sort |
Youngjae Lee |
title |
Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification |
title_short |
Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification |
title_full |
Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification |
title_fullStr |
Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification |
title_full_unstemmed |
Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification |
title_sort |
effect of probabilistic similarity measure on metric-based few-shot classification |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/7f50fb27736747cb881c6b3232758cdb |
work_keys_str_mv |
AT youngjaelee effectofprobabilisticsimilaritymeasureonmetricbasedfewshotclassification AT hyeyoungpark effectofprobabilisticsimilaritymeasureonmetricbasedfewshotclassification |
_version_ |
1718413028206051328 |