
A Computationally Efficient Neural Network Invariant to the Action of Symmetry Subgroups
We introduce a method to design a computationally efficient Ginvariant ...
read it

Finegrained Optimization of Deep Neural Networks
In recent studies, several asymptotic upper bounds on generalization err...
read it

Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment
We address a problem of estimating pose of a person's head from its RGB ...
read it

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
We revisit the problem of estimating depth of a scene from its single RG...
read it

Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
Researchers have applied deep neural networks to image restoration tasks...
read it

Deep Structured EnergyBased Image Inpainting
In this paper, we propose a structured image inpainting method employing...
read it

A vision based system for underwater docking
Autonomous underwater vehicles (AUVs) have been deployed for underwater ...
read it

HyperNetworks with statistical filtering for defending adversarial examples
Deep learning algorithms have been known to be vulnerable to adversarial...
read it

Linear Discriminant Generative Adversarial Networks
We develop a novel method for training of GANs for unsupervised and clas...
read it

Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs
In this work, we address the problem of improvement of robustness of fea...
read it

Information Potential AutoEncoders
In this paper, we suggest a framework to make use of mutual information ...
read it

Truncating Wide Networks using Binary Tree Architectures
Recent study shows that a wide deep network can obtain accuracy comparab...
read it

Optimization on Product Submanifolds of Convolution Kernels
Recent advances in optimization methods used for training convolutional ...
read it

Optimization on Submanifolds of Convolution Kernels in CNNs
Kernel normalization methods have been employed to improve robustness of...
read it

Encoding the Local Connectivity Patterns of fMRI for Cognitive State Classification
In this work, we propose a novel framework to encode the local connectiv...
read it

Hierarchical Multiresolution Mesh Networks for Brain Decoding
We propose a new framework, called Hierarchical Multiresolution Mesh Ne...
read it

Modeling the Sequence of Brain Volumes by Local Mesh Models for Brain Decoding
We represent the sequence of fMRI (Functional Magnetic Resonance Imaging...
read it

Design of Kernels in Convolutional Neural Networks for Image Classification
Despite the effectiveness of Convolutional Neural Networks (CNNs) for im...
read it

A Hierarchical Approach for Joint Multiview Object Pose Estimation and Categorization
We propose a joint object pose estimation and categorization approach wh...
read it

Fusion of Image Segmentation Algorithms using Consensus Clustering
A new segmentation fusion method is proposed that ensembles the output o...
read it

Semisupervised Segmentation Fusion of Multispectral and Aerial Images
A Semisupervised Segmentation Fusion algorithm is proposed using consen...
read it

A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid GenerativeDescriptive Model
A graph theoretic approach is proposed for object shape representation i...
read it

Discriminative Functional Connectivity Measures for Brain Decoding
We propose a statistical learning model for classifying cognitive proces...
read it

Mesh Learning for Classifying Cognitive Processes
A relatively recent advance in cognitive neuroscience has been multivox...
read it
Mete Ozay
is this you? claim profile
Research Fellow at the School of Computer Science, University of Birmingham, UK.