Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network

Chao Zhang; Fei Yang; Guoping Qiu; Qian Zhang

doi:10.1109/ICIP.2019.8802915

Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network

Chao Zhang, Fei Yang, Guoping Qiu, Qian Zhang

School of Computer Science

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

Salient Object Detection (SOD) is one significant research area which is closely correlated to the attention of human beings. Most of the nowadays CNN-based approaches for SOD are based on an U-Net architecture. In this paper, we propose a novel capsule-based salient object detection framework by integrating the novel capsule blocks into both the generator and discriminator of GAN architecture. The experimental result showed that our approach is able to generate accurate saliency maps, which also highlighted the effectiveness of the capsule blocks. We also provide a challenging dataset that contains 3,299 images for SOD with difficult foreground objects and complex background contents.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Publisher	IEEE Computer Society
Pages	81-85
Number of pages	5
ISBN (Electronic)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8802915
Publication status	Published - Sept 2019
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China Duration: 22 Sept 2019 → 25 Sept 2019

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2019-September
ISSN (Print)	1522-4880

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country/Territory	Taiwan, Province of China
City	Taipei
Period	22/09/19 → 25/09/19

Keywords

Capsule Net
Generative Adversarial Network
Image-level Saliency
Salient Object Detection
cGAN

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2019.8802915

Cite this

Zhang, C., Yang, F., Qiu, G., & Zhang, Q. (2019). Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network. In 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings (pp. 81-85). Article 8802915 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2019.8802915

@inproceedings{fa1e224ee32a495482bf75ac7ca642f1,

title = "Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network",

abstract = "Salient Object Detection (SOD) is one significant research area which is closely correlated to the attention of human beings. Most of the nowadays CNN-based approaches for SOD are based on an U-Net architecture. In this paper, we propose a novel capsule-based salient object detection framework by integrating the novel capsule blocks into both the generator and discriminator of GAN architecture. The experimental result showed that our approach is able to generate accurate saliency maps, which also highlighted the effectiveness of the capsule blocks. We also provide a challenging dataset that contains 3,299 images for SOD with difficult foreground objects and complex background contents.",

keywords = "Capsule Net, Generative Adversarial Network, Image-level Saliency, Salient Object Detection, cGAN",

author = "Chao Zhang and Fei Yang and Guoping Qiu and Qian Zhang",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICIP.2019.8802915",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "81--85",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

address = "United States",

}

Zhang, C, Yang, F, Qiu, G & Zhang, Q 2019, Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8802915, Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, IEEE Computer Society, pp. 81-85, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, Province of China, 22/09/19. https://doi.org/10.1109/ICIP.2019.8802915

Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network. / Zhang, Chao; Yang, Fei; Qiu, Guoping et al.
2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. IEEE Computer Society, 2019. p. 81-85 8802915 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network

AU - Zhang, Chao

AU - Yang, Fei

AU - Qiu, Guoping

AU - Zhang, Qian

PY - 2019/9

Y1 - 2019/9

N2 - Salient Object Detection (SOD) is one significant research area which is closely correlated to the attention of human beings. Most of the nowadays CNN-based approaches for SOD are based on an U-Net architecture. In this paper, we propose a novel capsule-based salient object detection framework by integrating the novel capsule blocks into both the generator and discriminator of GAN architecture. The experimental result showed that our approach is able to generate accurate saliency maps, which also highlighted the effectiveness of the capsule blocks. We also provide a challenging dataset that contains 3,299 images for SOD with difficult foreground objects and complex background contents.

AB - Salient Object Detection (SOD) is one significant research area which is closely correlated to the attention of human beings. Most of the nowadays CNN-based approaches for SOD are based on an U-Net architecture. In this paper, we propose a novel capsule-based salient object detection framework by integrating the novel capsule blocks into both the generator and discriminator of GAN architecture. The experimental result showed that our approach is able to generate accurate saliency maps, which also highlighted the effectiveness of the capsule blocks. We also provide a challenging dataset that contains 3,299 images for SOD with difficult foreground objects and complex background contents.

KW - Capsule Net

KW - Generative Adversarial Network

KW - Image-level Saliency

KW - Salient Object Detection

KW - cGAN

UR - http://www.scopus.com/inward/record.url?scp=85076798993&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2019.8802915

DO - 10.1109/ICIP.2019.8802915

M3 - Conference contribution

AN - SCOPUS:85076798993

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 81

EP - 85

BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings

PB - IEEE Computer Society

T2 - 26th IEEE International Conference on Image Processing, ICIP 2019

Y2 - 22 September 2019 through 25 September 2019

ER -

Salient Object Detection with Capsule-Based Conditional Generative Adversarial Network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this