Generalized Operational Classifiers for Material Identification

Xiaoyue Jiang, DIng Wang, Dat Thanh Tran, Serkan Kiranyaz, Moncef Gabbouj, Xiaoyi Feng

科研成果: 书/报告/会议事项章节会议稿件同行评审

2 引用 (Scopus)

摘要

Material is one of the intrinsic features of objects, and consequently material recognition plays an important role in image understanding. The same material may have various shapes and appearance, while keeping the same physical characteristic. This brings great challenges for material recognition. Besides suitable features, a powerful classifier also can improve the overall recognition performance. Due to the limitations of classical linear neurons, used in all shallow and deep neural networks, such as CNN, we propose to apply the generalized operational neurons to construct a classifier adaptively. These generalized operational perceptrons (GOP) contain a set of linear and nonlinear neurons, and possess a structure that can be built progressively. This makes GOP classifier more compact and can easily discriminate complex classes. The experiments demonstrate that GOP networks trained on a small portion of the data (4%) can achieve comparable performances to state-of-the-arts models trained on much larger portions of the dataset.

源语言英语
主期刊名IEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781728193205
DOI
出版状态已出版 - 21 9月 2020
活动22nd IEEE International Workshop on Multimedia Signal Processing, MMSP 2020 - Virtual, Tampere, 芬兰
期限: 21 9月 202024 9月 2020

出版系列

姓名IEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020

会议

会议22nd IEEE International Workshop on Multimedia Signal Processing, MMSP 2020
国家/地区芬兰
Virtual, Tampere
时期21/09/2024/09/20

指纹

探究 'Generalized Operational Classifiers for Material Identification' 的科研主题。它们共同构成独一无二的指纹。

引用此