Local Features and Visual Words Emerge in Activations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00337163" target="_blank" >RIV/68407700:21230/19:00337163 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8954470/keywords#keywords" target="_blank" >https://ieeexplore.ieee.org/document/8954470/keywords#keywords</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR.2019.01192" target="_blank" >10.1109/CVPR.2019.01192</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Local Features and Visual Words Emerge in Activations

Popis výsledku v původním jazyce

We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations by global pooling, as in recent state-of-the-art work. However, the same sparse 3D activation tensor is also approximated by a collection of local features. These local features are then robustly matched to approximate the optimal alignment of the tensors. This happens without any network modification, additional layers or training. No local feature detection happens on the original image. No local feature descriptors and no visual vocabulary are needed throughout the whole process. We experimentally show that the proposed method achieves the state-of-the-art performance on standard benchmarks across different network architectures and different global pooling methods. The highest gain in performance is achieved when diffusion on the nearest-neighbor graph of global descriptors is initiated from spatially verified images.

Název v anglickém jazyce

Local Features and Visual Words Emerge in Activations

Popis výsledku anglicky

We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations by global pooling, as in recent state-of-the-art work. However, the same sparse 3D activation tensor is also approximated by a collection of local features. These local features are then robustly matched to approximate the optimal alignment of the tensors. This happens without any network modification, additional layers or training. No local feature detection happens on the original image. No local feature descriptors and no visual vocabulary are needed throughout the whole process. We experimentally show that the proposed method achieves the state-of-the-art performance on standard benchmarks across different network architectures and different global pooling methods. The highest gain in performance is achieved when diffusion on the nearest-neighbor graph of global descriptors is initiated from spatially verified images.

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

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

CVPR 2019: Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition

ISBN

978-1-7281-3293-8

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

11643-11652

Název nakladatele

IEEE

Místo vydání

—

Místo konání akce

Long Beach

Datum konání akce

15. 6. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—