Lightweight Spectral-Spatial Squeeze-and-Excitation Residual Bag-of-Features Learning for Hyperspectral Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F20%3A10246262" target="_blank" >RIV/61989100:27240/20:10246262 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8976424" target="_blank" >https://ieeexplore.ieee.org/document/8976424</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TGRS.2019.2961681" target="_blank" >10.1109/TGRS.2019.2961681</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Lightweight Spectral-Spatial Squeeze-and-Excitation Residual Bag-of-Features Learning for Hyperspectral Classification

Popis výsledku v původním jazyce

Of late, convolutional neural networks (CNNs) find great attention in hyperspectral image (HSI) classification since deep CNNs exhibit commendable performance for computer vision-related areas. CNNs have already proved to be very effective feature extractors, especially for the classification of large data sets composed of 2-D images. However, due to the existence of noisy or correlated spectral bands in the spectral domain and nonuniform pixels in the spatial neighborhood, HSI classification results are often degraded and unacceptable. However, the elementary CNN models often find intrinsic representation of pattern directly when employed to explore the HSI in the spectral-spatial domain. In this article, we design an end-to-end spectral-spatial squeeze-and-excitation (SE) residual bag-of-feature (S3EResBoF) learning framework for HSI classification that takes as input raw 3-D image cubes without engineering and builds a codebook representation of transform feature by motivating the feature maps facilitating classification by suppressing useless feature maps based on patterns present in the feature maps. To boost the classification performance and learn the joint spatial-spectral features, every residual block is connected to every other 3-D convolutional layer through an identity mapping followed by an SE block, thereby facilitating the rich gradients through backpropagation. Additionally, we introduce batch normalization on every convolutional layer (ConvBN) to regularize the convergence of the network and scale invariant BoF quantization for the measure of classification.

Název v anglickém jazyce

Lightweight Spectral-Spatial Squeeze-and-Excitation Residual Bag-of-Features Learning for Hyperspectral Classification

Popis výsledku anglicky

Of late, convolutional neural networks (CNNs) find great attention in hyperspectral image (HSI) classification since deep CNNs exhibit commendable performance for computer vision-related areas. CNNs have already proved to be very effective feature extractors, especially for the classification of large data sets composed of 2-D images. However, due to the existence of noisy or correlated spectral bands in the spectral domain and nonuniform pixels in the spatial neighborhood, HSI classification results are often degraded and unacceptable. However, the elementary CNN models often find intrinsic representation of pattern directly when employed to explore the HSI in the spectral-spatial domain. In this article, we design an end-to-end spectral-spatial squeeze-and-excitation (SE) residual bag-of-feature (S3EResBoF) learning framework for HSI classification that takes as input raw 3-D image cubes without engineering and builds a codebook representation of transform feature by motivating the feature maps facilitating classification by suppressing useless feature maps based on patterns present in the feature maps. To boost the classification performance and learn the joint spatial-spectral features, every residual block is connected to every other 3-D convolutional layer through an identity mapping followed by an SE block, thereby facilitating the rich gradients through backpropagation. Additionally, we introduce batch normalization on every convolutional layer (ConvBN) to regularize the convergence of the network and scale invariant BoF quantization for the measure of classification.

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/EF17_049%2F0008425" target="_blank" >EF17_049/0008425: Platforma pro výzkum orientovaný na Průmysl 4.0 a robotiku v ostravské aglomeraci</a><br>

Návaznosti

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

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Geoscience and Remote Sensing

ISSN

0196-2892

e-ISSN

—

Svazek periodika

58

Číslo periodika v rámci svazku

8

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

5277-5290

Kód UT WoS článku

000552371900004

EID výsledku v databázi Scopus

2-s2.0-85086138500