On Visualizations in the Role of Universal Data Representation
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10420896" target="_blank" >RIV/00216208:11320/20:10420896 - isvavai.cz</a>
Výsledek na webu
<a href="https://doi.org/10.1145/3372278.3390743" target="_blank" >https://doi.org/10.1145/3372278.3390743</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/3372278.3390743" target="_blank" >10.1145/3372278.3390743</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
On Visualizations in the Role of Universal Data Representation
Popis výsledku v původním jazyce
The deep learning revolution changed the world of machine learning and boosted the AI industry as such. In particular, the most effective models for image retrieval are based on deep convolutional neural networks (DCNN), outperforming the traditional "hand-engineered" models by far. However, this tremendous success was redeemed by a high cost in the form of an exhaustive gathering of labeled data, followed by designing and training the DCNN models. In this paper, we outline a vision of a framework for instant transfer learning, where a generic pre-trained DCNN model is used as a universal feature extraction method for visualized unstructured data in many (non-visual) domains. The deep feature descriptors are then usable in similarity search tasks (database queries, joins) and in other parts of the data processing pipeline. The envisioned framework should enable practitioners to instantly use DCNN-based data representations in their new domains without the need for the costly training step. Moreover, by use of the framework the information visualization community could acquire a versatile metric for measuring the quality of data visualizations, which is generally a difficult task.
Název v anglickém jazyce
On Visualizations in the Role of Universal Data Representation
Popis výsledku anglicky
The deep learning revolution changed the world of machine learning and boosted the AI industry as such. In particular, the most effective models for image retrieval are based on deep convolutional neural networks (DCNN), outperforming the traditional "hand-engineered" models by far. However, this tremendous success was redeemed by a high cost in the form of an exhaustive gathering of labeled data, followed by designing and training the DCNN models. In this paper, we outline a vision of a framework for instant transfer learning, where a generic pre-trained DCNN model is used as a universal feature extraction method for visualized unstructured data in many (non-visual) domains. The deep feature descriptors are then usable in similarity search tasks (database queries, joins) and in other parts of the data processing pipeline. The envisioned framework should enable practitioners to instantly use DCNN-based data representations in their new domains without the need for the costly training step. Moreover, by use of the framework the information visualization community could acquire a versatile metric for measuring the quality of data visualizations, which is generally a difficult task.
Klasifikace
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)
Návaznosti výsledku
Projekt
<a href="/cs/project/GA19-01641S" target="_blank" >GA19-01641S: Kontextové podobnostní vyhledávání v otevřených datech</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2020
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the 2020 on International Conference on Multimedia Retrieval
ISBN
978-1-4503-7087-5
ISSN
—
e-ISSN
—
Počet stran výsledku
6
Strana od-do
362-367
Název nakladatele
ACM
Místo vydání
New York, NY, USA
Místo konání akce
Dublin, Irsko
Datum konání akce
26. 10. 2020
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—