Edge Augmentation for Large-Scale Sketch Recognition without Sketches

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00362153" target="_blank" >RIV/68407700:21230/22:00362153 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICPR56361.2022.9956233" target="_blank" >https://doi.org/10.1109/ICPR56361.2022.9956233</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICPR56361.2022.9956233" target="_blank" >10.1109/ICPR56361.2022.9956233</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Edge Augmentation for Large-Scale Sketch Recognition without Sketches

Popis výsledku v původním jazyce

This work addresses scaling up the sketch classification task into a large number of categories. Collecting sketches for training is a slow and tedious process that has so far precluded any attempts to large-scale sketch recognition. We overcome the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain. To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images. Randomization is introduced in the parameters of edge detection and edge selection. Natural images are translated to a pseudo-novel domain called "randomized Binary Thin Edges" (rBTE), which is used as a training domain instead of natural images. The ability to scale up is demonstrated by training CNN-based sketch recognition of more than 2.5 times larger number of categories than used previously. For this purpose, a dataset of natural images from 874 categories is constructed by combining a number of popular computer vision datasets. The categories are selected to be suitable for sketch recognition. To estimate the performance, a subset of 393 categories with sketches is also collected.

Název v anglickém jazyce

Edge Augmentation for Large-Scale Sketch Recognition without Sketches

Popis výsledku anglicky

This work addresses scaling up the sketch classification task into a large number of categories. Collecting sketches for training is a slow and tedious process that has so far precluded any attempts to large-scale sketch recognition. We overcome the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain. To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images. Randomization is introduced in the parameters of edge detection and edge selection. Natural images are translated to a pseudo-novel domain called "randomized Binary Thin Edges" (rBTE), which is used as a training domain instead of natural images. The ability to scale up is demonstrated by training CNN-based sketch recognition of more than 2.5 times larger number of categories than used previously. For this purpose, a dataset of natural images from 874 categories is constructed by combining a number of popular computer vision datasets. The categories are selected to be suitable for sketch recognition. To estimate the performance, a subset of 393 categories with sketches is also collected.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

2022 26th International Conference on Pattern Recognition (ICPR)

ISBN

978-1-6654-9062-7

ISSN

1051-4651

e-ISSN

2831-7475

Počet stran výsledku

8

Strana od-do

3595-3602

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Montreal

Datum konání akce

21. 8. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000897707603084