Active vision for deep visual learning: a unified pooling framework

Guo, Nan, Gu, Ke, Qiao, Junfei and Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 2022. Active vision for deep visual learning: a unified pooling framework. IEEE Transactions on Industrial Informatics 18 (10) , pp. 6610-6618. 10.1109/TII.2021.3129813

Preview

PDF - Accepted Post-Print Version Download (3MB) | Preview

Abstract

Convolutional Neural Networks (CNNs) can be generally regarded as learning-based visual systems for computer vision tasks. By imitating the operating mechanism of the human visual system (HVS), CNNs can even achieve better results than human beings in some visual tasks. However, they are primary when compared to the HVS for the reason that the HVS has the ability of active vision to promptly analyze and adapt to specific tasks. In this study, a new unified pooling framework was proposed and a series of pooling methods were designed based on the framework to implement active vision to CNNs. In addition, an active selection pooling (ASP) was put forward to reorganize existing and newly proposed pooling methods. The CNN models with ASP tend to have a behavior of focus selection according to tasks during training process, which acts extrememly similar to the HVS.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1551-3203
Date of First Compliant Deposit:	25 November 2021
Date of Acceptance:	3 November 2021
Last Modified:	30 Nov 2024 20:15
URI:	https://orca.cardiff.ac.uk/id/eprint/145757

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item