
Pyramidal Dense Attention Networks for Lightweight Image SuperResolution
Recently, deep convolutional neural network methods have achieved an exc...
read it

Feedback Pyramid Attention Networks for Single Image SuperResolution
Recently, convolutional neural network (CNN) based image superresolutio...
read it

TOHAN: A Onestep Approach towards Fewshot Hypothesis Adaptation
In fewshot domain adaptation (FDA), classifiers for the target domain a...
read it

SparseBERT: Rethinking the Importance Analysis in Selfattention
Transformerbased models are popular for natural language processing (NL...
read it

A Survey of Labelnoise Representation Learning: Past, Present and Future
Classical machine learning implicitly assumes that labels of the trainin...
read it

Efficient LowRank Matrix Learning by Factorizable Nonconvex Regularization
Matrix learning is at the core of many machine learning problems. To enc...
read it

Effective Decoding in Graph AutoEncoder using Triadic Closure
The (variational) graph autoencoder and its variants have been popularl...
read it

CommunicationEfficient Distributed Blockwise Momentum SGD with ErrorFeedback
Communication overhead is a major bottleneck hampering the scalability o...
read it

Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning
Stochastic methods with coordinatewise adaptive stepsize (such as RMSpr...
read it

General Convolutional Sparse Coding with Unknown Noise
Convolutional sparse coding (CSC) can learn representative shiftinvaria...
read it

Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
Variance reduction has been commonly used in stochastic optimization. It...
read it

Power Law in Sparsified Deep Neural Networks
The power law has been observed in the degree distributions of many biol...
read it

Online Convolutional Sparse Coding with SampleDependent Dictionary
Convolutional sparse coding (CSC) has been popularly used for the learni...
read it

Lossaware Weight Quantization of Deep Networks
The huge size of deep networks hinders their use in small computing devi...
read it

Scalable Robust Matrix Factorization with Nonconvex Loss
Robust matrix factorization (RMF), which uses the ℓ_1loss, often outper...
read it

Efficient Robust Matrix Factorization with Nonconvex Loss
Robust matrix factorization (RMF), which uses the ℓ_1loss, often outper...
read it

LargeScale LowRank Matrix Learning with Nonconvex Regularizers
Lowrank modeling has many important applications in computer vision and...
read it

Scalable Online Convolutional Sparse Coding
Convolutional sparse coding (CSC) improves sparse coding by learning a s...
read it

MultiLabel Learning with Global and Local Label Correlation
It is wellknown that exploiting label correlations is important to mult...
read it

Accelerated and Inexact SoftImpute for LargeScale Matrix and Tensor Completion
Matrix and tensor completion aim to recover a lowrank matrix / tensor f...
read it

Lossaware Binarization of Deep Networks
Deep neural network models, though very powerful and highly successful, ...
read it

Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity
The use of convex regularizers allows for easy optimization, though they...
read it

Stochastic VarianceReduced ADMM
The alternating direction method of multipliers (ADMM) is a powerful opt...
read it

Fast Nonsmooth Regularized Risk Minimization with Continuation
In regularized risk minimization, the associated optimization problem be...
read it

Fast LowRank Matrix Learning with Nonconvex Regularization
Lowrank modeling has a lot of important applications in machine learnin...
read it
James T. Kwok
is this you? claim profile
Professor in the Department of Computer Science and Engineering at Hong Kong University of Science and Technology