
MixPath: A Unified Approach for Oneshot Neural Architecture Search
The expressiveness of search space is a key concern in neural architectu...
read it

Triple Generative Adversarial Networks
Generative adversarial networks (GANs) have shown promise in image gener...
read it

Function Space Particle Optimization for Bayesian Neural Networks
While Bayesian neural networks (BNNs) have drawn increasing attention, t...
read it

Pruning from Scratch
Network pruning is an important research field aiming at reducing comput...
read it

Bringing Old Photos Back to Life
We propose to restore old photos that suffer from severe degradation thr...
read it

Fast, Accurate and Lightweight SuperResolution with Neural Architecture Search
Deep convolution neural networks demonstrate impressive results in super...
read it

Adversarial Variational Inference and Learning in Markov Random Fields
Markov random fields (MRFs) find applications in a variety of machine le...
read it

LIA: Latently Invertible Autoencoder with Adversarial Learning
Deep generative models play an increasingly important role in machine le...
read it

Realization of spatial sparseness by deep ReLU nets with massive data
The great success of deep learning poses urgent challenges for understan...
read it

DBSN: Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structures
Bayesian neural networks (BNNs) introduce uncertainty estimation to deep...
read it

Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
Differential Architecture Search (DARTS) is now a widely disseminated we...
read it

A DataCenter FPGA Acceleration Platform for Convolutional Neural Networks
Intensive computation is entering data centers with multiple workloads o...
read it

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
Score matching provides an effective approach to learning flexible unnor...
read it

Deep Structured Generative Models
Deep generative models have shown promising results in generating realis...
read it

Document Rectification and Illumination Correction using a Patchbased CNN
We propose a novel learning method to rectify document images with vario...
read it

Automatic quality assessment for 2D fetal sonographic standard plane based on multitask learning
The quality control of fetal sonographic (FS) images is essential for th...
read it

Blind Geometric Distortion Correction on Images Through Deep Learning
We propose the first general framework to automatically correct differen...
read it

Deep Exemplarbased Video Colorization
This paper presents the first endtoend network for exemplarbased vide...
read it

Latent Variables on Spheres for Sampling and Spherical Inference
Variational inference is a fundamental problem in Variational AutoEncod...
read it

Automatic, Dynamic, and Nearly Optimal Learning Rate Specification by Local Quadratic Approximation
In deep learning tasks, the learning rate determines the update step siz...
read it

Interlinked Convolutional Neural Networks for Face Parsing
Face parsing is a basic task in face image analysis. It amounts to label...
read it

Crossdomain Correspondence Learning for Exemplarbased Image Translation
We present a general framework for exemplarbased image translation, whi...
read it

Analyzing and Improving Stein Variational Gradient Descent for Highdimensional Marginal Inference
Stein variational gradient descent (SVGD) is a nonparametric inference m...
read it

Fast Deep Matting for Portrait Animation on Mobile Phone
Image matting plays an important role in image and video editing. Howeve...
read it

Discriminatively Boosted Image Clustering with Fully Convolutional AutoEncoders
Traditional image clustering methods take a twostep approach, feature l...
read it

Improving Interpretability of Deep Neural Networks with Semantic Information
Interpretability of deep neural networks (DNNs) is essential since it en...
read it

Triple Generative Adversarial Nets
Generative Adversarial Nets (GANs) have shown promise in image generatio...
read it

MaxMargin Deep Generative Models for (Semi)Supervised Learning
Deep generative models (DGMs) are effective on learning multilayered rep...
read it

Effective Deterministic Initialization for kMeansLike Methods via Local Density Peaks Searching
The kmeans clustering algorithm is popular but has the following main d...
read it

Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation
We present a discriminative nonparametric latent feature relational mode...
read it

Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
Hashing method maps similar data to binary hashcodes with smaller hammin...
read it

Bootstrapping Face Detection with Hard Negative Examples
Recently significant performance improvement in face detection was made ...
read it

Fast Sampling for Bayesian MaxMargin Models
Bayesian maxmargin models have shown superiority in various practical a...
read it

Planning and Acting under Uncertainty: A New Model for Spoken Dialogue Systems
Uncertainty plays a central role in spoken dialogue systems. Some stocha...
read it

Big Learning with Bayesian Methods
Explosive growth in data and availability of cheap computing resources h...
read it

A Novel Biologically MechanismBased Visual Cognition ModelAutomatic Extraction of Semantics, Formation of Integrated Concepts and Reselection Features for Ambiguity
Integration between biology and information science benefits both fields...
read it

Learning to Generate with Memory
Memory units have been widely used to enrich the capabilities of deep ne...
read it

Gibbs Maxmargin Topic Models with Data Augmentation
Maxmargin learning is a powerful approach to building classifiers and s...
read it

Discriminative Relational Topic Models
Many scientific and engineering fields involve analyzing network data. F...
read it

Improved Bayesian Logistic Supervised Topic Models with Data Augmentation
Supervised topic models with a logistic likelihood have two issues that ...
read it

Maxmargin Deep Generative Models
Deep generative models (DGMs) are effective on learning multilayered rep...
read it

A new embedding quality assessment method for manifold learning
Manifold learning is a hot research topic in the field of computer scien...
read it

Intrinsic dimension estimation of data by principal component analysis
Estimating intrinsic dimensionality of data is a classic problem in patt...
read it

An Explicit Nonlinear Mapping for Manifold Learning
Manifold learning is a hot research topic in the field of computer scien...
read it

Isometric MultiManifolds Learning
Isometric feature mapping (Isomap) is a promising manifold learning meth...
read it

SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
This paper presents a Semantic Attribute Modulation (SAM) for language m...
read it

Jointly Modeling Topics and Intents with Global Order Structure
Modeling document structure is of great importance for discourse analysi...
read it

Directional Modulation Design Based on CrossedDipole Arrays for Two Signals With Orthogonal Polarisations
Directional modulation (DM) is a physical layer security technique based...
read it

Smooth Neighbors on Teacher Graphs for Semisupervised Learning
The paper proposes an inductive semisupervised learning method, called ...
read it

Bearing fault diagnosis under varying working condition based on domain adaptation
Traditional intelligent fault diagnosis of rolling bearings work well on...
read it
Bo Zhang
is this you? claim profile
Professor of Department of Computer Science and Technology at Tsinghua University