
H2NFNet for Brain Tumor Segmentation using Multimodal MR Imaging: 2nd Place Solution to BraTS Challenge 2020 Segmentation Task
In this paper, we propose a Hybrid Highresolution and Nonlocal Feature...
read it

CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
Recent years have witnessed the emergence and flourishing of hierarchica...
read it

A Deep DriftDiffusion Model for Image Aesthetic Score Distribution Prediction
The task of aesthetic quality assessment is complicated due to its subje...
read it

Gradient Descent Ascent for MinMax Problems on Riemannian Manifold
In the paper, we study a class of useful nonconvex minimax optimization...
read it

Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee
Due to the hierarchical structure of many machine learning problems, bil...
read it

Periodic Stochastic Gradient Descent with Momentum for Decentralized Training
Decentralized training has been actively studied in recent years. Althou...
read it

Adaptive Serverless Learning
With the emergence of distributed data, training machine learning models...
read it

Accelerated ZerothOrder Momentum Methods from Mini to Minimax Optimization
In the paper, we propose a new accelerated zerothorder momentum (AccZO...
read it

PrivacyPreserving Asynchronous Federated Learning Algorithms for MultiParty Vertically Collaborative Learning
The privacypreserving federated learning for vertically partitioned dat...
read it

Training Faster with Compressed Gradient
Although the distributed machine learning methods show the potential for...
read it

Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
In this paper, we propose a faster stochastic alternating direction meth...
read it

MomentumBased Policy Gradient Methods
In the paper, we propose a class of efficient momentumbased policy grad...
read it

Fast OSCAR and OWL Regression via Safe Screening Rules
Ordered Weighted L_1 (OWL) regularized regression is a new regression an...
read it

Faster Secure Data Mining via Distributed Homomorphic Encryption
Due to the rising privacy demand in data mining, Homomorphic Encryption ...
read it

Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Reweighting
Unsupervised domain adaptation (UDA) for nuclei instance segmentation is...
read it

Exploit Where Optimizer Explores via Residuals
To train neural networks faster, many research efforts have been devoted...
read it

Optimal Gradient Quantization Condition for CommunicationEfficient Distributed Training
The communication of gradients is costly for training deep neural networ...
read it

Cell RCNN V3: A Novel Panoptic Paradigm for Instance Segmentation in Biomedical Images
Instance segmentation is an important task for biomedical image analysis...
read it

Large Batch Training Does Not Need Warmup
Training deep neural networks using a large batch size has shown promisi...
read it

Quadruply Stochastic Gradient Method for Large Scale Nonlinear SemiSupervised Ordinal Regression AUC Optimization
Semisupervised ordinal regression (S^2OR) problems are ubiquitous in re...
read it

Region and Object based Panoptic Image Synthesis through Conditional GANs
Imagetoimage translation is significant to many computer vision and ma...
read it

StragglerAgnostic and CommunicationEfficient Distributed PrimalDual Algorithm for HighDimensional Data Mining
Recently, reducing communication time between machines becomes the main ...
read it

Ouroboros: On Accelerating Training of TransformerBased Language Models
Language models are essential for natural language processing (NLP) task...
read it

Approaching Machine Learning Fairness through Adversarial Network
Fairness is becoming a rising concern w.r.t. machine learning model perf...
read it

Diversely Stale Parameters for Efficient Training of CNNs
The backpropagation algorithm is the most popular algorithm training neu...
read it

Nonconvex ZerothOrder Stochastic ADMM Methods with Lower Function Query Complexity
Zerothorder (gradientfree) method is a class of powerful optimization ...
read it

Quadruply Stochastic Gradients for Large Scale Nonlinear SemiSupervised AUC Optimization
Semisupervised learning is pervasive in realworld applications, where ...
read it

Scalable SemiSupervised SVM via Triply Stochastic Gradients
Semisupervised learning (SSL) plays an increasingly important role in t...
read it

An Iteratively Reweighted Method for Problems with SparsityInducing Norms
This work aims at solving the problems with intractable sparsityinducin...
read it

Robust Linear Discriminant Analysis Using Ratio Minimization of L1,2Norms
As one of the most popular linear subspace learning methods, the Linear ...
read it

ZerothOrder Stochastic Alternating Direction Method of Multipliers for Nonconvex Nonsmooth Optimization
Alternating direction method of multipliers (ADMM) is a popular optimiza...
read it

LightTrack: A Generic Framework for Online TopDown Human Pose Tracking
In this paper, we propose a novel effective lightweight framework, call...
read it

Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
In this paper, we propose a novel endtoend trainable Video Question An...
read it

Faster GradientFree Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization
Proximal gradient method has been playing an important role to solve man...
read it

3D Global Convolutional Adversarial Network for Prostate MR Volume Segmentation
Advanced deep learning methods have been developed to conduct prostate M...
read it

Training Neural Networks Using Features Replay
Training a neural network using backpropagation algorithm requires passi...
read it

Decoupled Parallel Backpropagation with Convergence Guarantee
Backpropagation algorithm is indispensable for the training of feedforwa...
read it

Medical Image Segmentation Based on MultiModal Convolutional Neural Network: Study on Image Fusion Schemes
Image analysis using more than one modality (i.e. multimodal) has been ...
read it

Fast and Scalable Distributed Deep Convolutional Autoencoder for fMRI Big Data Analytics
In recent years, analyzing taskbased fMRI (tfMRI) data has become an es...
read it

A Harmonic Mean Linear Discriminant Analysis for Robust Image Classification
Linear Discriminant Analysis (LDA) is a widelyused supervised dimension...
read it

Enhancing Sentence Relation Modeling with Auxiliary Characterlevel Embedding
Neural network based approaches for sentence relation modeling automatic...
read it

Clinical Information Extraction via Convolutional Neural Network
We report an implementation of a clinical information extraction tool th...
read it

Theoretic Analysis and Extremely Easy Algorithms for Domain Adaptive Feature Learning
Domain adaptation problems arise in a variety of applications, where a t...
read it

An Iterative Locally Linear Embedding Algorithm
Local Linear embedding (LLE) is a popular dimension reduction method. In...
read it

Are Tensor Decomposition Solutions Unique? On the global convergence of HOSVD and ParaFac algorithms
For tensor decompositions such as HOSVD and ParaFac, the objective funct...
read it
Heng Huang
is this you? claim profile