Outdoor scene labelling with learned features and region consistency activation

Research output: Chapter in Book/Conference paperConference paper

2 Citations (Scopus)

Abstract

© 2015 IEEE. This paper presents a learned feature based method for scene labelling. This method is combined with a novel strategy to improve global label consistency. We first follow a traditional way to investigate trained features from convolutional neural networks (ConvNets) for scene labelling. Then, motivated by the recent successful use of general features extracted from ConvNets for various applications, we extend the use of the general features to scene labelling (for the first time). We further propose an algorithm called Region Consistency Activation (RCA) to improve the global label consistency. RCA is based on a novel transformation between Ultrametric Contour Map (UCM) and the Probability of Regions Consistency (PRC). Our algorithms were rigorously tested on the popular Stanford Background and SIFT Flow datasets. We achieved superior performances compared with the state-of-the-art methods on both of these datasets.
Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1374-1378
Volume2015-December
ISBN (Print)9781479983391
DOIs
Publication statusPublished - 2015
Event2015 IEEE International Conference on Image Processing - Quebec City, Canada
Duration: 27 Sep 201530 Sep 2015

Conference

Conference2015 IEEE International Conference on Image Processing
CountryCanada
CityQuebec City
Period27/09/1530/09/15

Fingerprint

Labeling
Chemical activation
Labels
Neural networks

Cite this

Li, Y., Sohel, F., Bennamoun, M., & Lei, H. (2015). Outdoor scene labelling with learned features and region consistency activation. In Proceedings - International Conference on Image Processing, ICIP (Vol. 2015-December, pp. 1374-1378). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2015.7351025
Li, Y ; Sohel, Ferdous ; Bennamoun, Mohammed ; Lei, H. / Outdoor scene labelling with learned features and region consistency activation. Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 1374-1378
@inproceedings{6aa52cc504b84977b8bc829bc80618b2,
title = "Outdoor scene labelling with learned features and region consistency activation",
abstract = "{\circledC} 2015 IEEE. This paper presents a learned feature based method for scene labelling. This method is combined with a novel strategy to improve global label consistency. We first follow a traditional way to investigate trained features from convolutional neural networks (ConvNets) for scene labelling. Then, motivated by the recent successful use of general features extracted from ConvNets for various applications, we extend the use of the general features to scene labelling (for the first time). We further propose an algorithm called Region Consistency Activation (RCA) to improve the global label consistency. RCA is based on a novel transformation between Ultrametric Contour Map (UCM) and the Probability of Regions Consistency (PRC). Our algorithms were rigorously tested on the popular Stanford Background and SIFT Flow datasets. We achieved superior performances compared with the state-of-the-art methods on both of these datasets.",
author = "Y Li and Ferdous Sohel and Mohammed Bennamoun and H. Lei",
year = "2015",
doi = "10.1109/ICIP.2015.7351025",
language = "English",
isbn = "9781479983391",
volume = "2015-December",
pages = "1374--1378",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Li, Y, Sohel, F, Bennamoun, M & Lei, H 2015, Outdoor scene labelling with learned features and region consistency activation. in Proceedings - International Conference on Image Processing, ICIP. vol. 2015-December, IEEE, Institute of Electrical and Electronics Engineers, pp. 1374-1378, 2015 IEEE International Conference on Image Processing, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7351025

Outdoor scene labelling with learned features and region consistency activation. / Li, Y; Sohel, Ferdous; Bennamoun, Mohammed; Lei, H.

Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 1374-1378.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Outdoor scene labelling with learned features and region consistency activation

AU - Li, Y

AU - Sohel, Ferdous

AU - Bennamoun, Mohammed

AU - Lei, H.

PY - 2015

Y1 - 2015

N2 - © 2015 IEEE. This paper presents a learned feature based method for scene labelling. This method is combined with a novel strategy to improve global label consistency. We first follow a traditional way to investigate trained features from convolutional neural networks (ConvNets) for scene labelling. Then, motivated by the recent successful use of general features extracted from ConvNets for various applications, we extend the use of the general features to scene labelling (for the first time). We further propose an algorithm called Region Consistency Activation (RCA) to improve the global label consistency. RCA is based on a novel transformation between Ultrametric Contour Map (UCM) and the Probability of Regions Consistency (PRC). Our algorithms were rigorously tested on the popular Stanford Background and SIFT Flow datasets. We achieved superior performances compared with the state-of-the-art methods on both of these datasets.

AB - © 2015 IEEE. This paper presents a learned feature based method for scene labelling. This method is combined with a novel strategy to improve global label consistency. We first follow a traditional way to investigate trained features from convolutional neural networks (ConvNets) for scene labelling. Then, motivated by the recent successful use of general features extracted from ConvNets for various applications, we extend the use of the general features to scene labelling (for the first time). We further propose an algorithm called Region Consistency Activation (RCA) to improve the global label consistency. RCA is based on a novel transformation between Ultrametric Contour Map (UCM) and the Probability of Regions Consistency (PRC). Our algorithms were rigorously tested on the popular Stanford Background and SIFT Flow datasets. We achieved superior performances compared with the state-of-the-art methods on both of these datasets.

U2 - 10.1109/ICIP.2015.7351025

DO - 10.1109/ICIP.2015.7351025

M3 - Conference paper

SN - 9781479983391

VL - 2015-December

SP - 1374

EP - 1378

BT - Proceedings - International Conference on Image Processing, ICIP

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Li Y, Sohel F, Bennamoun M, Lei H. Outdoor scene labelling with learned features and region consistency activation. In Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December. IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 1374-1378 https://doi.org/10.1109/ICIP.2015.7351025