Mar 18, 2017 · In this study, we designed a powerful method, FDCNet, which can accurately learn marine organisms. FDCNet classifies deep-sea objects better ...
The proposed filtering deep convolutional network (FDCNet) classifies deep-sea objects better than state-of-the-art classification methods, such as AlexNet, ...
The proposed filtering deep convolutional network (FDCNet) classifies deep-sea objects better than state-of-the-art classification methods, such as AlexNet, ...
The classification accuracy of the proposed FDCNet method is 1.8%, 2.9%, 2.0%, and 1.0% better than AlexNet, GooLeNet, ResNet50, and ResNet101, respectively. In ...
filtering deep convolutional network for marine organism classification.
search.ebscohost.com › login
Abstract: Convolutional networks are currently the most popular computer vision methods for a wide variety of applications in multimedia research fields.
Oct 22, 2024 · The classification accuracy of the proposed FDCNet method is 1.8%, 2.9%, 2.0%, and 1.0% better than AlexNet, GooLeNet, ResNet50, and ResNet101, ...
A seminal contribution in this field is the development of the filtering deep convolutional network (FDCNet) (Lu et al., 2018) , which effectively classifies ...
In this study, we develop a powerful approach that can accurately learn marine organisms. The proposed filtering deep convolutional network (FDCNet) classifies ...
Convolutional networks are currently the most popular computer vision methods for a wide variety of applications in multimedia research fields.
Sep 19, 2023 · Lu et al. (2018) used the filtering deep convolutional network (FDCNet) classifier to identify the most relevant features. The results showed ...