Adaptive convolution kernel for artificial neural networks
MetadataShow full item record
CitationTek, F. B., Çam, İ. & Karlı, D. (2021). Adaptive convolution kernel for artificial neural networks. Journal of Visual Communication and Image Representation, 75, 1-11.doi:10.1016/j.jvcir.2020.103015
Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3 × 3) kernels. This paper describes a method for learning the size of convolutional kernels to provide varying size kernels in a single layer. The method utilizes a differentiable, and therefore backpropagation-trainable Gaussian envelope which can grow or shrink in a base grid. Our experiments compared the proposed adaptive layers to ordinary convolution layers in a simple two-layer network, a deeper residual network, and a U-Net architecture. The results in the popular image classification datasets such as MNIST, MNIST-CLUTTERED, CIFAR-10, Fashion, and ‘‘Faces in the Wild’’ showed that the adaptive kernels can provide statistically significant improvements on ordinary convolution kernels. A segmentation experiment in the Oxford-Pets dataset demonstrated that replacing ordinary convolution layers in a U-shaped network with 7 × 7 adaptive layers can improve its learning performance and ability to generalize.
SourceJournal of Visual Communication and Image Representation
The following license files are associated with this item:
Showing items related by title, author, creator and subject.
In this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed ...
Süberk, Nilay Tuğçe; Ateş, Hasan Fehmi (Institute of Electrical and Electronics Engineers Inc., 2019-09)Bu bildiri, derin öğrenme yöntemleri uygulayarak uzaktan algılamalı optik görüntülerde bina yoğunluğunun noktasal olarak kestirilmesi ile ilgilidir. Bu çalışma kapsamında, evrişimsel sinir ağına (ESA) dayalı derin öğrenme ...
Tek, Faik Boray (Elsevier B.V., 2021-01-02)This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic ...