Search Results for author: Gustavo K. Rohde

Found 28 papers, 17 papers with code

Sliced Wasserstein Auto-Encoders

1 code implementation ICLR 2019 Soheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde

In this paper we use the geometric properties of the optimal transport (OT) problem and the Wasserstein distances to define a prior distribution for the latent space of an auto-encoder.

Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model

5 code implementations5 Apr 2018 Soheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde

In short, we regularize the autoencoder loss with the sliced-Wasserstein distance between the distribution of the encoded training samples and a predefined samplable distribution.

Sliced Wasserstein Distance for Learning Gaussian Mixture Models

2 code implementations CVPR 2018 Soheil Kolouri, Gustavo K. Rohde, Heiko Hoffmann

In contrast to the KL-divergence, the energy landscape for the sliced-Wasserstein distance is more well-behaved and therefore more suitable for a stochastic gradient descent scheme to obtain the optimal GMM parameters.

Generalized Sliced Wasserstein Distances

1 code implementation NeurIPS 2019 Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau, Gustavo K. Rohde

The SW distance, specifically, was shown to have similar properties to the Wasserstein distance, while being much simpler to compute, and is therefore used in various applications including generative modeling and general supervised/unsupervised learning.

The Signed Cumulative Distribution Transform for 1-D Signal Analysis and Classification

1 code implementation3 Jun 2021 Akram Aldroubi, Rocio Diaz Martin, Ivan Medri, Gustavo K. Rohde, Sumati Thareja

This paper presents a new mathematical signal transform that is especially suitable for decoding information related to non-rigid signal displacements.

Translation

Invariance encoding in sliced-Wasserstein space for image classification with limited training data

2 code implementations9 Jan 2022 Mohammad Shifat E Rabbi, Yan Zhuang, Shiying Li, Abu Hasnat Mohammad Rubaiyat, Xuwang Yin, Gustavo K. Rohde

However, they are known to underperform when training data are limited and thus require data augmentation strategies that render the method computationally expensive and not always effective.

Data Augmentation Image Classification

End-to-End Signal Classification in Signed Cumulative Distribution Transform Space

1 code implementation30 Apr 2022 Abu Hasnat Mohammad Rubaiyat, Shiying Li, Xuwang Yin, Mohammad Shifat E Rabbi, Yan Zhuang, Gustavo K. Rohde

This paper presents a new end-to-end signal classification method using the signed cumulative distribution transform (SCDT).

Classification

Wasserstein Embedding for Graph Learning

1 code implementation ICLR 2021 Soheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, Heiko Hoffmann

We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast framework for embedding entire graphs in a vector space, in which various machine learning models are applicable for graph-level prediction tasks.

Computational Efficiency Graph Classification +4

Cell image classification: a comparative overview

1 code implementation7 Jun 2019 Mohammad Shifat-E-Rabbi, Xuwang Yin, Cailey Elizabeth Fitzgerald, Gustavo K. Rohde

Cell image classification methods are currently being used in numerous applications in cell biology and medicine.

Classification Image Classification

Neural Networks, Hypersurfaces, and Radon Transforms

1 code implementation4 Jul 2019 Soheil Kolouri, Xuwang Yin, Gustavo K. Rohde

Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks.

Learning Energy-Based Models With Adversarial Training

1 code implementation11 Dec 2020 Xuwang Yin, Shiying Li, Gustavo K. Rohde

We study a new approach to learning energy-based models (EBMs) based on adversarial training (AT).

Adversarial Defense Adversarial Robustness +3

GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification

1 code implementation27 May 2019 Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde

The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.

Classification General Classification +2

Transport-Based Pattern Theory: A Signal Transformation Approach

no code implementations20 Feb 2018 Liam Cattell, Gustavo K. Rohde

In this work we describe an approach for simultaneous modeling and inference of such data, using the mathematics of optimal transport.

Discovery and visualization of structural biomarkers from MRI using transport-based morphometry

no code implementations14 May 2017 Shinjini Kundu, Soheil Kolouri, Kirk I Erickson, Arthur F Kramer, Edward McAuley, Gustavo K. Rohde

Disease in the brain is often associated with subtle, spatially diffuse, or complex tissue changes that may lie beneath the level of gross visual inspection, even on magnetic resonance imaging (MRI).

blind source separation

A Transportation $L^p$ Distance for Signal Analysis

no code implementations27 Sep 2016 Matthew Thorpe, Serim Park, Soheil Kolouri, Gustavo K. Rohde, Dejan Slepčev

Transport based distances, such as the Wasserstein distance and earth mover's distance, have been shown to be an effective tool in signal and image analysis.

The Radon cumulative distribution transform and its application to image classification

no code implementations10 Nov 2015 Soheil Kolouri, Se Rim Park, Gustavo K. Rohde

Invertible image representation methods (transforms) are routinely employed as low-level image processing operations based on which feature extraction and recognition algorithms are developed.

General Classification Image Classification

Sliced Wasserstein Kernels for Probability Distributions

no code implementations CVPR 2016 Soheil Kolouri, Yang Zou, Gustavo K. Rohde

Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions.

BIG-bench Machine Learning

Transport-Based Single Frame Super Resolution of Very Low Resolution Face Images

no code implementations CVPR 2015 Soheil Kolouri, Gustavo K. Rohde

Extracting high-resolution information from highly degraded facial images is an important problem with several applications in science and technology.

Super-Resolution

Partitioning signal classes using transport transforms for data analysis and machine learning

no code implementations8 Aug 2020 Akram Aldroubi, Shiying Li, Gustavo K. Rohde

A relatively new set of transport-based transforms (CDT, R-CDT, LOT) have shown their strength and great potential in various image and data processing tasks such as parametric signal estimation, classification, cancer detection among many others.

BIG-bench Machine Learning Classification +1

GAT: Generative Adversarial Training for Adversarial Example Detection and Classification

no code implementations ICLR 2020 Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde

The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.

General Classification Robust classification +1

Geodesic Properties of a Generalized Wasserstein Embedding for Time Series Analysis

no code implementations4 Jun 2022 Shiying Li, Abu Hasnat Mohammad Rubaiyat, Gustavo K. Rohde

Transport-based metrics and related embeddings (transforms) have recently been used to model signal classes where nonlinear structures or variations are present.

Time Series Time Series Analysis

LCOT: Linear circular optimal transport

no code implementations9 Oct 2023 Rocio Diaz Martin, Ivan Medri, Yikun Bai, Xinran Liu, Kangbai Yan, Gustavo K. Rohde, Soheil Kolouri

The optimal transport problem for measures supported on non-Euclidean spaces has recently gained ample interest in diverse applications involving representation learning.

Representation Learning

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