
SelfNorm and CrossNorm for OutofDistribution Robustness
Normalization techniques are crucial in stabilizing and accelerating the...
read it

Improving Machine Reading Comprehension with Singlechoice Decision and Transfer Learning
Multichoice Machine Reading Comprehension (MMRC) aims to select the cor...
read it

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
Graph neural networks (GNNs) are gaining increasing popularity as a prom...
read it

CSER: Communicationefficient SGD with Error Reset
The scalability of Distributed Stochastic Gradient Descent (SGD) is toda...
read it

Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes
BERT has recently attracted a lot of attention in natural language under...
read it

Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
Modern deep neural networks increasingly make use of features such as dy...
read it

Learning ContextBased Nonlocal Entropy Modeling for Image Compression
The entropy of the codes usually serves as the rate loss in the recent l...
read it

Improving Semantic Segmentation via SelfTraining
Deep learning usually achieves the best results with complete supervisio...
read it

ResNeSt: SplitAttention Networks
While image classification models have recently continued to advance, mo...
read it

AutoGluonTabular: Robust and Accurate AutoML for Structured Data
We introduce AutoGluonTabular, an opensource AutoML framework that req...
read it

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer...
read it

A Unified Optimization Approach for CNN Model Inference on Integrated GPUs
Modern deep learning applications urge to push the model inference takin...
read it

Efficient and Effective ContextBased Convolutional Entropy Modeling for Image Compression
It has long been understood that precisely estimating the probabilistic ...
read it

Dynamic Minibatch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
With an increasing demand for training powers for deep learning algorith...
read it

Language Models with Transformers
The Transformer architecture is superior to RNNbased models in computat...
read it

Learning ContentWeighted Deep Image Compression
Learningbased lossy image compression usually involves the joint optimi...
read it

Bag of Freebies for Training Object Detection Neural Networks
Comparing with enormous research achievements targeting better image cla...
read it

Bag of Tricks for Image Classification with Convolutional Neural Networks
Much of the recent progress made in image classification research can be...
read it

Optimizing CNN Model Inference on CPUs
The popularity of Convolutional Neural Network (CNN) models and the ubiq...
read it

Approximate Distribution Matching for SequencetoSequence Learning
SequencetoSequence models were introduced to tackle many reallife pro...
read it

Style Transfer as Unsupervised Machine Translation
Language style transferring rephrases text with specific stylistic attri...
read it

Regularizing Neural Machine Translation by Targetbidirectional Agreement
Although Neural Machine Translation (NMT) has achieved remarkable progre...
read it

Triangular Architecture for Rare Language Translation
Neural Machine Translation (NMT) performs poor on the lowresource langu...
read it

Achieving Human Parity on Automatic Chinese to English News Translation
Machine translation has made rapid advances in recent years. Millions of...
read it

Joint Training for Neural Machine Translation Models with Monolingual Data
Monolingual data have been demonstrated to be helpful in improving trans...
read it

ShiftNet: Image Inpainting via Deep Feature Rearrangement
Deep convolutional networks (CNNs) have exhibited their potential in ima...
read it

Efficient Trimmed Convolutional Arithmetic Encoding for Lossless Image Compression
Arithmetic encoding is an essential class of coding techniques which hav...
read it

Generative Bridging Network in Neural Sequence Prediction
Maximum Likelihood Estimation (MLE) suffers from data sparsity problem i...
read it

Learning Convolutional Networks for Contentweighted Image Compression
Lossy image compression is generally formulated as a joint ratedistorti...
read it

Deep Identityaware Transfer of Facial Attributes
This paper presents a Deep convolutional network model for IdentityAwar...
read it

Convolutional Network for Attributedriven and Identitypreserving Human Face Generation
This paper focuses on the problem of generating human face pictures from...
read it

Implicit Distortion and Fertility Models for Attentionbased EncoderDecoder NMT Model
Neural machine translation has shown very promising results lately. Most...
read it

Data Driven Resource Allocation for Distributed Learning
In distributed machine learning, data is dispatched to multiple machines...
read it

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
MXNet is a multilanguage machine learning (ML) library to ease the deve...
read it

High Performance Latent Variable Models
Latent variable models have accumulated a considerable amount of interes...
read it

AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization
We study distributed stochastic convex optimization under the delayed gr...
read it

Graph Partitioning via Parallel Submodular Approximation to Accelerate Distributed Machine Learning
Distributed computing excels at processing large scale data, but the com...
read it

Empirical Evaluation of Rectified Activations in Convolutional Network
In this paper we investigate the performance of different types of recti...
read it

Beyond Wordbased Language Model in Statistical Machine Translation
Language model is one of the most important modules in statistical machi...
read it