HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION

Peng Kang; Hao Hu; Srutarshi Banerjee; Henry Chopp; Aggelos Katsaggelos; Oliver Cossairt

doi:10.1109/ICIP42928.2021.9506331

HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION

Peng Kang, Hao Hu, Srutarshi Banerjee, Henry Chopp, Aggelos Katsaggelos, Oliver Cossairt

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Previous research always solely utilizes Artificial Neural Networks (ANNs) or Spiking Neural Networks (SNNs) for object recognition. However, evidence in neuroscience suggests that the visual processing in human vision is performed hierarchically in the combination of analog and digital processing. To construct a more human vision-like object recognition system, we propose a general hierarchical ANN-SNN model. We evaluate our model and its variants on two popular datasets to show its effectiveness, robustness, efficiency, and generality. Extensive experiments clearly demonstrate the superiority of our proposed models for robust object recognition.

Original language	English (US)
Title of host publication	2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
Publisher	IEEE Computer Society
Pages	709-713
Number of pages	5
ISBN (Electronic)	9781665441155
DOIs	https://doi.org/10.1109/ICIP42928.2021.9506331
State	Published - 2021
Event	2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States Duration: Sep 19 2021 → Sep 22 2021

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2021-September
ISSN (Print)	1522-4880

Conference

Conference	2021 IEEE International Conference on Image Processing, ICIP 2021
Country/Territory	United States
City	Anchorage
Period	9/19/21 → 9/22/21

Keywords

Artificial Neural Networks
Human vision
Robust object recogniton
Spiking Neural Networks

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP42928.2021.9506331

Cite this

Kang, P., Hu, H., Banerjee, S., Chopp, H., Katsaggelos, A., & Cossairt, O. (2021). HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION. In 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings (pp. 709-713). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September). IEEE Computer Society. https://doi.org/10.1109/ICIP42928.2021.9506331

@inproceedings{79459c70d4ee48b58e300bf55ea2599c,

title = "HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION",

abstract = "Previous research always solely utilizes Artificial Neural Networks (ANNs) or Spiking Neural Networks (SNNs) for object recognition. However, evidence in neuroscience suggests that the visual processing in human vision is performed hierarchically in the combination of analog and digital processing. To construct a more human vision-like object recognition system, we propose a general hierarchical ANN-SNN model. We evaluate our model and its variants on two popular datasets to show its effectiveness, robustness, efficiency, and generality. Extensive experiments clearly demonstrate the superiority of our proposed models for robust object recognition.",

keywords = "Artificial Neural Networks, Human vision, Robust object recogniton, Spiking Neural Networks",

author = "Peng Kang and Hao Hu and Srutarshi Banerjee and Henry Chopp and Aggelos Katsaggelos and Oliver Cossairt",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Image Processing, ICIP 2021 ; Conference date: 19-09-2021 Through 22-09-2021",

year = "2021",

doi = "10.1109/ICIP42928.2021.9506331",

language = "English (US)",

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

publisher = "IEEE Computer Society",

pages = "709--713",

booktitle = "2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings",

address = "United States",

}

Kang, P, Hu, H, Banerjee, S, Chopp, H, Katsaggelos, A & Cossairt, O 2021, HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION. in 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2021-September, IEEE Computer Society, pp. 709-713, 2021 IEEE International Conference on Image Processing, ICIP 2021, Anchorage, United States, 9/19/21. https://doi.org/10.1109/ICIP42928.2021.9506331

HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION. / Kang, Peng; Hu, Hao; Banerjee, Srutarshi et al.
2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. IEEE Computer Society, 2021. p. 709-713 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION

AU - Kang, Peng

AU - Hu, Hao

AU - Banerjee, Srutarshi

AU - Chopp, Henry

AU - Katsaggelos, Aggelos

AU - Cossairt, Oliver

PY - 2021

Y1 - 2021

N2 - Previous research always solely utilizes Artificial Neural Networks (ANNs) or Spiking Neural Networks (SNNs) for object recognition. However, evidence in neuroscience suggests that the visual processing in human vision is performed hierarchically in the combination of analog and digital processing. To construct a more human vision-like object recognition system, we propose a general hierarchical ANN-SNN model. We evaluate our model and its variants on two popular datasets to show its effectiveness, robustness, efficiency, and generality. Extensive experiments clearly demonstrate the superiority of our proposed models for robust object recognition.

AB - Previous research always solely utilizes Artificial Neural Networks (ANNs) or Spiking Neural Networks (SNNs) for object recognition. However, evidence in neuroscience suggests that the visual processing in human vision is performed hierarchically in the combination of analog and digital processing. To construct a more human vision-like object recognition system, we propose a general hierarchical ANN-SNN model. We evaluate our model and its variants on two popular datasets to show its effectiveness, robustness, efficiency, and generality. Extensive experiments clearly demonstrate the superiority of our proposed models for robust object recognition.

KW - Artificial Neural Networks

KW - Human vision

KW - Robust object recogniton

KW - Spiking Neural Networks

UR - http://www.scopus.com/inward/record.url?scp=85125600502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125600502&partnerID=8YFLogxK

U2 - 10.1109/ICIP42928.2021.9506331

DO - 10.1109/ICIP42928.2021.9506331

M3 - Conference contribution

AN - SCOPUS:85125600502

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 709

EP - 713

BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings

PB - IEEE Computer Society

T2 - 2021 IEEE International Conference on Image Processing, ICIP 2021

Y2 - 19 September 2021 through 22 September 2021

ER -

HUMAN VISION-LIKE ROBUST OBJECT RECOGNITION

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this