Offset equivariant networks and their applications

被引:5
作者
Cotogni, Marco [1 ]
Cusano, Claudio [1 ]
机构
[1] Univ Pavia, Dept Elect Comp & Biomed Engn, Via Ferrata 1, I-27100 Pavia, Italy
关键词
Equivariant neural networks; Convolutional neural network; Image recognition; Illuminant estimation; Inpainting; NEURAL-NETWORK;
D O I
10.1016/j.neucom.2022.06.118
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we present a framework for the design and implementation of offset equivariant networks, that is, neural networks that preserve in their output uniform increments in the input. In a suitable color space this kind of networks achieves equivariance with respect to the photometric transformations that characterize changes in the lighting conditions. We verified the framework on three different problems: image recognition, illuminant estimation, and image inpainting. Our experiments show that the performance of offset equivariant networks are comparable to those in the state of the art on regular data. Differently from conventional networks, however, equivariant networks do behave consistently well when the color of the illuminant changes. (C) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页码:110 / 119
页数:10
相关论文
共 47 条
[41]  
Warde-Farley D., 2013, INT C MACH LEARN ATL, P1319
[42]   Deep Multi-View Enhancement Hashing for Image Retrieval [J].
Yan, Chenggang ;
Gong, Biao ;
Wei, Yuxuan ;
Gao, Yue .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (04) :1445-1451
[43]   Age-Invariant Face Recognition by Multi-Feature Fusion and Decomposition with Self-attention [J].
Yan, Chenggang ;
Meng, Lixuan ;
Li, Liang ;
Zhang, Jiehua ;
Wang, Zhan ;
Yin, Jian ;
Zhang, Jiyong ;
Sun, Yaoqi ;
Zheng, Bolun .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 18 (01)
[44]   Precise No-Reference Image Quality Evaluation Based on Distortion Identification [J].
Yan, Chenggang ;
Teng, Tong ;
Liu, Yutao ;
Zhang, Yongbing ;
Wang, Haoqian ;
Ji, Xiangyang .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 17 (03)
[45]   Task-Adaptive Attention for Image Captioning [J].
Yan, Chenggang ;
Hao, Yiming ;
Li, Liang ;
Yin, Jian ;
Liu, Anan ;
Mao, Zhendong ;
Chen, Zhenyu ;
Gao, Xingyu .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (01) :43-51
[46]   Depth Image Denoising Using Nuclear Norm and Learning Graph Model [J].
Yan, Chenggang ;
Li, Zhisheng ;
Zhang, Yongbing ;
Liu, Yutao ;
Ji, Xiangyang ;
Zhang, Yongdong .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 16 (04)
[47]   Universal Approximations of Invariant Maps by Neural Networks [J].
Yarotsky, Dmitry .
CONSTRUCTIVE APPROXIMATION, 2022, 55 (01) :407-474