Show simple item record

AuthorJiang X.
AuthorWang D.
AuthorTran D.T.
AuthorKiranyaz, Mustafa Serkan
AuthorGabbouj M.
AuthorFeng X.
Available date2022-04-26T12:31:19Z
Publication Date2020
Publication NameIEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020
ResourceScopus
Identifierhttp://dx.doi.org/10.1109/MMSP48831.2020.9287058
URIhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85099207385&doi=10.1109%2fMMSP48831.2020.9287058&partnerID=40&md5=272ac8fffa73419155ed9c80307c2e60
URIhttp://hdl.handle.net/10576/30604
AbstractMaterial 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.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectArts computing
Deep neural networks
Neural networks
Neurons
Complex class
Intrinsic features
Material identification
Material recognition
Non-linear neurons
Physical characteristics
State of the art
Multimedia signal processing
TitleGeneralized Operational Classifiers for Material Identification
TypeConference Paper
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record