Visualizations for universal deep-feature representations: survey and taxonomy

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10469887" target="_blank" >RIV/00216208:11320/24:10469887 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=tq1aSBp7US" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=tq1aSBp7US</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10115-023-01933-3" target="_blank" >10.1007/s10115-023-01933-3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Visualizations for universal deep-feature representations: survey and taxonomy

Popis výsledku v původním jazyce

In data science and content-based retrieval, we find many domain-specific techniques that employ a data processing pipeline with two fundamental steps. First, data entities are represented by some visualizations, while in the second step, the visualizations are used with a machine learning model to extract deep features. Deep convolutional neural networks (DCNN) became the standard and reliable choice. The purpose of using DCNN is either a specific classification task or just a deep feature representation of visual data for additional processing (e.g., similarity search). Whereas the deep feature extraction is a domain-agnostic step in the pipeline (inference of an arbitrary visual input), the visualization design itself is domain-dependent and ad hoc for every use case. In this paper, we survey and analyze many instances of data visualizations used with deep learning models (mostly DCNN) for domain-specific tasks. Based on the analysis, we synthesize a taxonomy that provides a systematic overview of visualization techniques suitable for usage with the models. The aim of the taxonomy is to enable the future generalization of the visualization design process to become completely domain-agnostic, leading to the automation of the entire feature extraction pipeline. As the ultimate goal, such an automated pipeline could lead to universal deep feature data representations for content-based retrieval.

Název v anglickém jazyce

Visualizations for universal deep-feature representations: survey and taxonomy

Popis výsledku anglicky

In data science and content-based retrieval, we find many domain-specific techniques that employ a data processing pipeline with two fundamental steps. First, data entities are represented by some visualizations, while in the second step, the visualizations are used with a machine learning model to extract deep features. Deep convolutional neural networks (DCNN) became the standard and reliable choice. The purpose of using DCNN is either a specific classification task or just a deep feature representation of visual data for additional processing (e.g., similarity search). Whereas the deep feature extraction is a domain-agnostic step in the pipeline (inference of an arbitrary visual input), the visualization design itself is domain-dependent and ad hoc for every use case. In this paper, we survey and analyze many instances of data visualizations used with deep learning models (mostly DCNN) for domain-specific tasks. Based on the analysis, we synthesize a taxonomy that provides a systematic overview of visualization techniques suitable for usage with the models. The aim of the taxonomy is to enable the future generalization of the visualization design process to become completely domain-agnostic, leading to the automation of the entire feature extraction pipeline. As the ultimate goal, such an automated pipeline could lead to universal deep feature data representations for content-based retrieval.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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/GA22-21696S" target="_blank" >GA22-21696S: Hluboké vizuální reprezentace nestrukturovaných dat</a><br>

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Knowledge and Information Systems

ISSN

0219-1377

e-ISSN

0219-3116

Svazek periodika

66

Číslo periodika v rámci svazku

February

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

30

Strana od-do

811-840

Kód UT WoS článku

001066953600004

EID výsledku v databázi Scopus

—