TY - GEN
T1 - Generalized Operational Classifiers for Material Identification
AU - Jiang, Xiaoyue
AU - Wang, DIng
AU - Tran, Dat Thanh
AU - Kiranyaz, Serkan
AU - Gabbouj, Moncef
AU - Feng, Xiaoyi
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/21
Y1 - 2020/9/21
N2 - 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.
AB - 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.
KW - generalized operational perceptrons
KW - material identification
UR - http://www.scopus.com/inward/record.url?scp=85099207385&partnerID=8YFLogxK
U2 - 10.1109/MMSP48831.2020.9287058
DO - 10.1109/MMSP48831.2020.9287058
M3 - 会议稿件
AN - SCOPUS:85099207385
T3 - IEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020
BT - IEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE International Workshop on Multimedia Signal Processing, MMSP 2020
Y2 - 21 September 2020 through 24 September 2020
ER -