Search Results for author: Trac. D. Tran

Found 23 papers, 7 papers with code

A Scale Invariant Flatness Measure for Deep Network Minima

no code implementations6 Feb 2019 Akshay Rangamani, Nam H. Nguyen, Abhishek Kumar, Dzung Phan, Sang H. Chin, Trac. D. Tran

It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization.

Reducing Sampling Ratios Improves Bagging in Sparse Regression

no code implementations20 Dec 2018 Luoluo Liu, Sang Peter Chin, Trac. D. Tran

With a properly chosen sampling ratio, a reasonably small number of estimates K = 30 gives satisfying result, even though increasing K is discovered to always improve or at least maintain the performance.


Generative Adversarial Networks for Recovering Missing Spectral Information

no code implementations11 Dec 2018 Dung N. Tran, Trac. D. Tran, Lam Nguyen

Ultra-wideband (UWB) radar systems nowadays typical operate in the low frequency spectrum to achieve penetration capability.

JOBS: Joint-Sparse Optimization from Bootstrap Samples

no code implementations8 Oct 2018 Luoluo Liu, Sang Peter Chin, Trac. D. Tran

In practice, it is often the case that not all measurements are available or required for recovery.

Supervised Deep Sparse Coding Networks

1 code implementation29 Jan 2017 Xiaoxia Sun, Nasser M. Nasrabadi, Trac. D. Tran

In this paper, we describe the deep sparse coding network (SCN), a novel deep network that encodes intermediate representations with nonnegative sparse coding.

General Classification

Linear Disentangled Representation Learning for Facial Actions

2 code implementations11 Jan 2017 Xiang Xiang, Trac. D. Tran

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features.

Facial Action Unit Detection Representation Learning +1

Adversarial Deep Structural Networks for Mammographic Mass Segmentation

1 code implementation18 Dec 2016 Wentao Zhu, Xiang Xiang, Trac. D. Tran, Xiaohui Xie

Experimental results on two public datasets, INbreast and DDSM-BCRP, show that our end-to-end network combined with adversarial training achieves the-state-of-the-art results.

Pose-Selective Max Pooling for Measuring Similarity

2 code implementations22 Sep 2016 Xiang Xiang, Trac. D. Tran

In this paper, we deal with two challenges for measuring the similarity of the subject identities in practical video-based face recognition - the variation of the head pose in uncontrolled environments and the computational expense of processing videos.

Face Recognition Face Verification +1

Sparse Coding with Fast Image Alignment via Large Displacement Optical Flow

no code implementations21 Dec 2015 Xiaoxia Sun, Nasser M. Nasrabadi, Trac. D. Tran

Sparse representation-based classifiers have shown outstanding accuracy and robustness in image classification tasks even with the presence of intense noise and occlusion.

Dictionary Learning Image Classification +1

ICR: Iterative Convex Refinement for Sparse Signal Recovery Using Spike and Slab Priors

no code implementations16 Feb 2015 Hojjat S. Mousavi, Vishal Monga, Trac. D. Tran

Essentially, ICR solves a sequence of convex optimization problems such that sequence of solutions converges to a sub-optimal solution of the original hard optimization problem.

Task-Driven Dictionary Learning for Hyperspectral Image Classification with Structured Sparsity Constraints

no code implementations3 Feb 2015 Xiaoxia Sun, Nasser M. Nasrabadi, Trac. D. Tran

We propose to enforce structured sparsity priors on the task-driven dictionary learning method in order to improve the performance of the hyperspectral classification.

Dictionary Learning General Classification +1

Multi-task Image Classification via Collaborative, Hierarchical Spike-and-Slab Priors

no code implementations30 Jan 2015 Hojjat Seyed Mousavi, Umamahesh Srinivas, Vishal Monga, Yuanming Suo, Minh Dao, Trac. D. Tran

Promising results have been achieved in image classification problems by exploiting the discriminative power of sparse representations for classification (SRC).

Classification Face Recognition +2

Collaborative Multi-sensor Classification via Sparsity-based Representation

no code implementations29 Oct 2014 Minh Dao, Nam H. Nguyen, Nasser M. Nasrabadi, Trac. D. Tran

In this paper, we propose a general collaborative sparse representation framework for multi-sensor classification, which takes into account the correlations as well as complementary information between heterogeneous sensors simultaneously while considering joint sparsity within each sensor's observations.

Classification General Classification

Hierarchical Sparse and Collaborative Low-Rank Representation for Emotion Recognition

1 code implementation7 Oct 2014 Xiang Xiang, Minh Dao, Gregory D. Hager, Trac. D. Tran

In this paper, we design a Collaborative-Hierarchical Sparse and Low-Rank (C-HiSLR) model that is natural for recognizing human emotion in visual data.

Emotion Recognition General Classification +1

Structured Priors for Sparse-Representation-Based Hyperspectral Image Classification

no code implementations16 Jan 2014 Xiaoxia Sun, Qing Qu, Nasser M. Nasrabadi, Trac. D. Tran

Pixel-wise classification, where each pixel is assigned to a predefined class, is one of the most important procedures in hyperspectral image (HSI) analysis.

Classification General Classification +1

Robust Lasso with missing and grossly corrupted observations

no code implementations NeurIPS 2011 Nasser M. Nasrabadi, Trac. D. Tran, Nam Nguyen

Our second set of results applies to a general class of Gaussian design matrix $X$ with i. i. d rows $\oper N(0, \Sigma)$, for which we provide a surprising phenomenon: the extended Lasso can recover exact signed supports of both $\beta^{\star}$ and $e^{\star}$ from only $\Omega(k \log p \log n)$ observations, even the fraction of corruption is arbitrarily close to one.

Discriminative Local Sparse Representations for Robust Face Recognition

no code implementations8 Nov 2011 Yi Chen, Umamahesh Srinivas, Thong T. Do, Vishal Monga, Trac. D. Tran

We propose a probabilistic graphical model framework to explicitly mine the conditional dependencies between these distinct sparse local features.

Face Recognition General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.