Gated Contextual Features for Salient Object Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F21%3A50017956" target="_blank" >RIV/62690094:18450/21:50017956 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9371722" target="_blank" >https://ieeexplore.ieee.org/document/9371722</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TIM.2021.3064423" target="_blank" >10.1109/TIM.2021.3064423</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Gated Contextual Features for Salient Object Detection

Popis výsledku v původním jazyce

The effective extraction of local and contextual visual cues carrying information of different scales is crucial for accurate detection of the salient object(s) with varying shape, size, and location. The Atrous Spatial Pyramid Pooling (ASPP) and its dense versions are widely used for extracting contextual features for dense prediction tasks. The skip connections in densely or moderately connected ASPP directly propagate the context information from a parallel dilated convolution to the next higher-rate dilated convolution to combat the “gridding issue” in àtrous convolutions. The aggregated context from several scales may dilute features belonging to small objects or confuse between the salient object and the background. To emphasize invariance features for different scale visual patterns in an image, a gate-based context extraction module is proposed in this work. Gate functions are embedded in the inter-branch short connection of the proposed module. The learnable gates are deployed to decide on the relevance of the contextual information extracted at a lower scale for the next higher scale. Experimental results on salient object detection task demonstrate that gates are helpful to retain relevant contextual information across multiple-scales of the context-extraction module. The performance of the proposed gated contextual feature-based salient object detector is evaluated on five broadly used saliency detection benchmarks by comparing it with the other 13 state-of-the-art approaches. Experimental outcomes show that the proposed method achieves a favorable performance for various compared evaluation measures. IEEE

Název v anglickém jazyce

Gated Contextual Features for Salient Object Detection

Popis výsledku anglicky

The effective extraction of local and contextual visual cues carrying information of different scales is crucial for accurate detection of the salient object(s) with varying shape, size, and location. The Atrous Spatial Pyramid Pooling (ASPP) and its dense versions are widely used for extracting contextual features for dense prediction tasks. The skip connections in densely or moderately connected ASPP directly propagate the context information from a parallel dilated convolution to the next higher-rate dilated convolution to combat the “gridding issue” in àtrous convolutions. The aggregated context from several scales may dilute features belonging to small objects or confuse between the salient object and the background. To emphasize invariance features for different scale visual patterns in an image, a gate-based context extraction module is proposed in this work. Gate functions are embedded in the inter-branch short connection of the proposed module. The learnable gates are deployed to decide on the relevance of the contextual information extracted at a lower scale for the next higher scale. Experimental results on salient object detection task demonstrate that gates are helpful to retain relevant contextual information across multiple-scales of the context-extraction module. The performance of the proposed gated contextual feature-based salient object detector is evaluated on five broadly used saliency detection benchmarks by comparing it with the other 13 state-of-the-art approaches. Experimental outcomes show that the proposed method achieves a favorable performance for various compared evaluation measures. IEEE

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

21101 - Food and beverages

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Instrumentation and Measurement

ISSN

0018-9456

e-ISSN

—

Svazek periodika

70

Číslo periodika v rámci svazku

March

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

"Article Number: 5007613"

Kód UT WoS článku

000731626300022

EID výsledku v databázi Scopus

2-s2.0-85102622466