Search Results for author: Hamid Krim

Found 23 papers, 2 papers with code

Information Fusion: Scaling Subspace-Driven Approaches

no code implementations26 Apr 2022 Sally Ghanem, Hamid Krim

In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Network (CNN) formalism.

Refining Self-Supervised Learning in Imaging: Beyond Linear Metric

no code implementations25 Feb 2022 Bo Jiang, Hamid Krim, Tianfu Wu, Derya Cansever

We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning.

Contrastive Learning Self-Supervised Learning

Deep Transform and Metric Learning Networks

no code implementations21 Apr 2021 Wen Tang, Emilie Chouzenoux, Jean-Christophe Pesquet, Hamid Krim

Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest.

Dictionary Learning Metric Learning

Latent Code-Based Fusion: A Volterra Neural Network Approach

no code implementations10 Apr 2021 Sally Ghanem, Siddharth Roheda, Hamid Krim

We propose a deep structure encoder using the recently introduced Volterra Neural Networks (VNNs) to seek a latent representation of multi-modal data whose features are jointly captured by a union of subspaces.

Robust classification

Robust Group Subspace Recovery: A New Approach for Multi-Modality Data Fusion

no code implementations18 Jun 2020 Sally Ghanem, Ashkan Panahi, Hamid Krim, Ryan A. Kerekes

Robust Subspace Recovery (RoSuRe) algorithm was recently introduced as a principled and numerically efficient algorithm that unfolds underlying Unions of Subspaces (UoS) structure, present in the data.

Time Series

Deep Transform and Metric Learning Network: Wedding Deep Dictionary Learning and Neural Networks

no code implementations18 Feb 2020 Wen Tang, Emilie Chouzenoux, Jean-Christophe Pesquet, Hamid Krim

On account of its many successes in inference tasks and denoising applications, Dictionary Learning (DL) and its related sparse optimization problems have garnered a lot of research interest.

Denoising Dictionary Learning +1

Volterra Neural Networks (VNNs)

no code implementations21 Oct 2019 Siddharth Roheda, Hamid Krim

The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals in ML, and particularly in Deep Learning.

Action Recognition Optical Flow Estimation

Community Detection and Improved Detectability in Multiplex Networks

no code implementations23 Sep 2019 Yuming Huang, Ashkan Panahi, Hamid Krim, Liyi Dai

We further demonstrate by numerical experiments that in the presence of consistent communities between different layers, consistent communities are matched, and the detectability is improved over a single layer.

Community Detection Stochastic Block Model

Deep Adversarial Belief Networks

no code implementations13 Sep 2019 Yuming Huang, Ashkan Panahi, Hamid Krim, Yiyi Yu, Spencer L. Smith

We present a novel adversarial framework for training deep belief networks (DBNs), which includes replacing the generator network in the methodology of generative adversarial networks (GANs) with a DBN and developing a highly parallelizable numerical algorithm for training the resulting architecture in a stochastic manner.

Computer Vision

Sparse Generative Adversarial Network

no code implementations20 Aug 2019 Shahin Mahdizadehaghdam, Ashkan Panahi, Hamid Krim

To that end we start by dividing an image into multiple patches and modifying the role of the generative network from producing an entire image, at once, to creating a sparse representation vector for each image patch.

Joint Concept Matching based Learning for Zero-Shot Recognition

no code implementations13 Jun 2019 Wen Tang, Ashkan Panahi, Hamid Krim

Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes.

Zero-Shot Learning

Robust Multi-Modal Sensor Fusion: An Adversarial Approach

no code implementations10 Jun 2019 Siddharth Roheda, Hamid Krim, Benjamin S. Riggan

Exploiting complementary information from different sensors, we show that target detection and classification problems can greatly benefit from this fusion approach and result in a performance increase.

Analysis Dictionary Learning: An Efficient and Discriminative Solution

no code implementations7 Mar 2019 Wen Tang, Ashkan Panahi, Hamid Krim, Liyi Dai

Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems.

Dictionary Learning General Classification +1

Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks

no code implementations20 Jul 2018 Siddharth Roheda, Benjamin S. Riggan, Hamid Krim, Liyi Dai

In this paper, we propose to use a Conditional Generative Adversarial Network (CGAN) for distilling (i. e. transferring) knowledge from sensor data and enhancing low-resolution target detection.

Analysis Dictionary Learning based Classification: Structure for Robustness

1 code implementation13 Jul 2018 Wen Tang, Ashkan Panahi, Hamid Krim, Liyi Dai

A consensus structured analysis dictionary and a global classifier are jointly learned in the distributed approach to safeguard the discriminative power and the efficiency of classification.

Classification Dictionary Learning +1

Structured Analysis Dictionary Learning for Image Classification

1 code implementation2 May 2018 Wen Tang, Ashkan Panahi, Hamid Krim, Liyi Dai

We propose a computationally efficient and high-performance classification algorithm by incorporating class structural information in analysis dictionary learning.

Classification Dictionary Learning +2

Demystifying Deep Learning: A Geometric Approach to Iterative Projections

no code implementations22 Mar 2018 Ashkan Panahi, Hamid Krim, Liyi Dai

Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e. g. number of layers in DL).

Deep Dictionary Learning: A PARametric NETwork Approach

no code implementations11 Mar 2018 Shahin Mahdizadehaghdam, Ashkan Panahi, Hamid Krim, Liyi Dai

Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics.

Benchmark Classification +3

First Study on Data Readiness Level

no code implementations18 Jan 2017 Hui Guan, Thanos Gentimis, Hamid Krim, James Keiser

We introduce the idea of Data Readiness Level (DRL) to measure the relative richness of data to answer specific questions often encountered by data scientists.

Effective Connectivity-Based Neural Decoding: A Causal Interaction-Driven Approach

no code implementations24 Jul 2016 Saba Emrani, Hamid Krim

We propose a geometric model-free causality measurebased on multivariate delay embedding that can efficiently detect linear and nonlinear causal interactions between time series with no prior information.

Time Series

Robust Detection of Periodic Patterns in Gene Expression Microarray Data using Topological Signal Analysis

no code implementations2 Oct 2014 Saba Emrani, Hamid Krim

In this paper, we present a new approach for analyzing gene expression data that builds on topological characteristics of time series.

Quantitative Methods Algebraic Topology Genomics

Robust Subspace Recovery via Bi-Sparsity Pursuit

no code implementations31 Mar 2014 Xiao Bian, Hamid Krim

Successful applications of sparse models in computer vision and machine learning imply that in many real-world applications, high dimensional data is distributed in a union of low dimensional subspaces.

Computer Vision

Persistent Homology of Delay Embeddings

no code implementations16 May 2013 Saba Emrani, Thanos Gentimis, Hamid Krim

The objective of this study is to detect and quantify the periodic behavior of the signals using topological methods.

Algebraic Topology 55N35, 55N99, 55U99

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