Unsupervised object discovery for instance recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00327162" target="_blank" >RIV/68407700:21230/18:00327162 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/WACV.2018.00194" target="_blank" >http://dx.doi.org/10.1109/WACV.2018.00194</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV.2018.00194" target="_blank" >10.1109/WACV.2018.00194</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised object discovery for instance recognition

Popis výsledku v původním jazyce

Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects.

Název v anglickém jazyce

Unsupervised object discovery for instance recognition

Popis výsledku anglicky

Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects.

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/LL1303" target="_blank" >LL1303: Vyhledávání vizuálních kategorií ve velkém množství obrázků</a><br>

Návaznosti

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

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018

ISBN

978-1-5386-4886-5

ISSN

2472-6737

e-ISSN

—

Počet stran výsledku

10

Strana od-do

1745-1754

Název nakladatele

Institute of Electrical and Electronics Engineers Inc

Místo vydání

—

Místo konání akce

Lake Tahoe

Datum konání akce

12. 3. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000434349200188