Home /
Research
Showing 25 - 30 / 897
Factor Normalization for Deep Neural Network Models
Anonymous....
Published date-01/01/2021
Deep neural network (DNN) models often involve features of ultrahigh dimensions. In most cases, the ultrahigh dimensional features can be decomposed into two parts. The first part is a low-dimensional …
NODE-SELECT: A FLEXIBLE GRAPH NEURAL NETWORK BASED ON REALISTIC PROPAGATION SCHEME
Anonymous....
Published date-01/01/2021
NodeClassification
While there exists a wide variety of graph neural networks (GNN) for node classification, only a minority of them adopt effective mechanisms to propagate the nodes' information with respect to …
Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
Anonymous....
Published date-01/01/2021
ImageGeneration
Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for …
LambdaNetworks: Modeling long-range Interactions without Attention
Anonymous....
Published date-01/01/2021
ImageClassification, InstanceSegmentation, ObjectDetection, SceneSegmentation, SemanticSegmentation
We present a general framework for capturing long-range interactions between an input and structured contextual information (e.g. a pixel surrounded by other pixels). Our method, called the lambda layer, captures …
Removing Undesirable Feature Contributions Using Out-of-Distribution Data
Anonymous....
Published date-01/01/2021
DataAugmentation
Several data augmentation methods deploy unlabeled-in-distribution (UID) data to bridge the gap between the training and inference of neural networks. However, these methods have clear limitations in terms of availability …
Dynamic Graph Representation Learning with Fourier Temporal State Embedding
Anonymous....
Published date-01/01/2021
GraphEmbedding, GraphRepresentationLearning, RepresentationLearning
Static graph representation learning has been applied in many tasks over the years thanks to the invention of unsupervised graph embedding methods and more recently, graph neural networks (GNNs). However, …