-
Convolutional-LSTM for Multi-Image to Single Output Medical Prediction
Medical head CT-scan imaging has been successfully combined with deep learning for medical diagnostics of head diseases and lesions. A custom dataset was used for this study. -
Texture vs Shape
This dataset is used to evaluate CNNs and human observers on images with a texture-shape cue conflict. -
Interpretable computer aided diagnosis of breast masses
The proposed interpretable CADx framework is devised to provide the diagnostic decision with interpretation in terms of medical descriptions (BI-RADS). -
MIXED PRECISION TRAINING
The dataset used for training deep neural networks using half-precision floating point numbers. -
Balanced Binary Neural Networks with Gated Residual
Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the... -
Visual Context-Aware Convolution Filters for Transformation-Invariant Neural ...
The proposed framework generates a unique set of context-dependent filters based on the input image, and combines them with max-pooling to produce transformation-invariant... -
QuadConv: Quadrature-based convolutions with applications to non-uniform PDE ...
QuadConv: Quadrature-based convolutions with applications to non-uniform PDE data compression. -
Learning Graph Neural Networks with Approximate Gradient Descent
The dataset used in the paper is a graph neural network (GNN) dataset, where the goal is to learn a GNN with one hidden layer for node information convolution. -
ProGroTrack: Deep Learning-Assisted Tracking of Intracellular Protein Growth ...
The dataset used in this paper for tracking intracellular protein growth dynamics. -
SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used various neural networks, including AlexNet, VGG16, InceptionV4, ResNet50,... -
RotDCF: Rotation-Equivariant Deep Networks
The paper proposes a decomposition of the convolutional filters over joint steerable bases across the space and the group geometry simultaneously, namely a rotation-equivariant... -
CIC 2020: Challenge on Learned Image Compression
The CIC 2020 dataset is a collection of images with different compression methods. -
A Data-Centric Optimization Framework for Machine Learning
DaCeML is a Data-Centric Machine Learning framework that provides a simple, flexible, and customizable pipeline for optimizing training of arbitrary deep neural networks. -
Resource-Frugal Classification and Analysis of Pathology Slides Using Image E...
Pathology slides of lung malignancies are classified using resource-frugal convolution neural networks (CNNs) that may be deployed on mobile devices. -
Predicting mrna abundance directly from genomic sequence using deep convoluti...
A dataset for predicting gene expression from genomic sequence using deep convolutional neural networks. -
Depth Separation with Intra-layer Links
The dataset used in the paper is a collection of functions that can be represented by a deep network, but cannot be represented by a shallow network. -
Optimization of Inf-Convolution Regularized Nonconvex Composite Problems
The dataset used in this paper is a stochastic distributed training dataset for deep neural networks. -
Frequency Centric Defense Mechanisms against Adversarial Examples
The proposed work uses the magnitude and phase of the Fourier Spectrum and the entropy of the image to defend against Adversarial Examples. -
Deep Epitomic Convolutional Neural Networks
Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new...
