Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research topics from publications: RENOIR – A dataset for real low-light image noise reduction; Feature Selection with Annealing for Computer Vision and Big Data Learning; Prediction of the crack condition of highway pavements using machine learning models; Pavement Crack Rating Using Machine Learning Frameworks: Partitioning, Bootstrap Forest, Boosted Trees, Naïve Bayes, and K -Nearest Neighbors; Prolonged treatment with open-label pirfenidone in Hermansky-Pudlak syndrome pulmonary fibrosis; Parameterized principal component analysis; An analysis of robust cost functions for CNN in computer-aided diagnosis; Face detection with a 3D model; Are screening methods useful in feature selection? An empirical study; Introduction to Monte Carlo Methods. Representative work: Many computer vision and medical imaging problems are faced with learning from large-scale datasets, with millions of observations and features. In this paper we propose a novel efficient learning scheme that tightens a sparsity constraint by gradually removing variables based on a criterion and a schedule. The attractive fact that the problem size keeps dropping throughout the iterations makes it particularly suitable for big data learning. Our approach applies generically to the optimization of any differentiable loss function, and finds applications in regression, classification and ranking. The resultant algorithms build variable screening into estimation and are extremely simple to impl Departments of Transportation regularly evaluate the condition of pavements through visual inspections, nondestructive evaluations, image recognition models and learning algorithms. The above methodologies, though efficient, have drawn attention due to their subjective errors, uncertainties, noise effects and overfitting. To improve on the outcomes of the shallow learning models already used in pavement crack prediction, this paper reports on an investigation of the use of recursive partitioning and artificial neural networks (ANN; deep learning frameworks) in predicting the crack rating of pavements. Explanatory variables such as the average daily traffic and truck factor, roadway functiona
A novel framework for online supervised learning with feature selection
Scalable Clustering: Large Scale Unsupervised Learning of Gaussian Mixture Models with Outliers
PCA-UNET for Object Segmentation
Large-Scale Few-Shot Classification with Semi-supervised Hierarchical k-Probabilistic PCAs
Slow Kill for Big Data Learning
Training a Two-Layer ReLU Network Analytically
Machine-learning of piezoelectric coefficients for wurtzite crystals
Hierarchical Classification for Large-Scale Learning
Online Feature Screening for Data Streams With Concept Drift
Scalable Learning with Incremental Probabilistic PCA
Fast 3D Liver Segmentation Using a Trained Deep Chan-Vese Model
A Study of Shape Modeling Against Noise
Network Pruning via Annealing and Direct Sparsity Control
The Compact Support Neural Network
Predicting Lane Change Decision Making with Compact Support
Swendsen-Wang Cut Algorithm
A Study of Local Optima for Learning Feature Interactions using Neural Networks
Introduction to Monte Carlo Methods
The Generalization-Stability Tradeoff In Neural Network Pruning
OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) 2020cited by 5position: middle
Hamiltonian and Langevin Monte Carlo
Training a Steerable CNN for Guidewire Detection
Neural Rule Ensembles: Encoding Sparse Feature Interactions into Neural Networks
Convergence Analysis of MCMC
Data Driven Markov Chain Monte Carlo
Mapping the Energy Landscape
Metropolis Methods and Variants