In this paper, we use the ideas presented in [1] to construct application-targeted convolutional neural network architectures (CNN). Specifically, we design frame filter banks consisting of sparse kernels with custom-selected orientations that can act as finite-difference operators. We then use these filter banks as the building blocks of structured receptive field CNNs [2] to compare baseline models with more application-oriented methods. Our tests are done on Google's Quick, Draw! data set.
Deep neural networks have achieved impressive performance in problems of object detection and object category classifications. To perform efficiently though, such methods typically require a large number of training samples. Unfortunately, this requirement is highly impractical or impossible in applications such as hyperspectral classification where it is expensive and labor intensive to generate labeled data for training. A few ideas have been proposed in the literature to address this problem such as transfer learning and domain adaptation. In this work, we propose an alternative strategy to reduce the number of network parameters based on Structured Receptive Field Networks (SRFN), a class of convolutional neural networks (CNNs) where each convolutional filter is a linear combination from a predefined dictionary. To better exploit the characteristics of hyperspectral data to be learned, we choose a filter dictionary consisting of directional filters inspired by the theory of shearlets and we train a SRFN by imposing that the convolutional filters form sparse linear combinations in such dictionary. The application of our SRFN to problems of hyperspectral classification shows that this approach achieves very competitive performance as compared to conventional CNNs.
Spines are protrusions of neuronal dendritic surfaces. These subcellular compartments are essential in neuronal information processing since electrical signals from other neurons are transmitted to dendrites via synaptic gateways located at dendritic spines. One of the important tasks for assessing synaptic strength is estimating the volume of spines, which is quite challenging because the image resolution for spines in live animal microscopy images is low and the level of noise is high. In order to carry out this task we develop a method for spine surface segmentation using sparse representations based on directional 3D filters with small spatial support.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.