Search Results for author: Guillermo Sapiro

Found 78 papers, 14 papers with code

Federating for Learning Group Fair Models

no code implementations5 Oct 2021 Afroditi Papadaki, Natalia Martinez, Martin Bertran, Guillermo Sapiro, Miguel Rodrigues

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models.

Fairness Federated Learning

Adversarial Factor Models for the Generation of Improved Autism Diagnostic Biomarkers

no code implementations24 Sep 2021 William E. Carson IV, Dmitry Isaev, Samatha Major, Guillermo Sapiro, Geraldine Dawson, David Carlson

Second, we show this same model can be used to learn a disentangled representation of multimodal biomarkers that results in an increase in predictive performance.

GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

1 code implementation30 Apr 2021 Chenfei Wu, Lun Huang, Qianxi Zhang, Binyang Li, Lei Ji, Fan Yang, Guillermo Sapiro, Nan Duan

Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation.

Video Generation

ReaPER: Improving Sample Efficiency in Model-Based Latent Imagination

no code implementations1 Jan 2021 Martin A Bertran, Guillermo Sapiro, Mariano Phielipp

Deep Reinforcement Learning (DRL) can distill behavioural policies from sensory input that solve complex tasks, however, the policies tend to be task-specific and sample inefficient, requiring a large number of interactions with the environment that may be costly or impractical for many real world applications.

Blind Pareto Fairness and Subgroup Robustness

no code implementations1 Jan 2021 Natalia Martinez, Martin Bertran, Afroditi Papadaki, Miguel R. D. Rodrigues, Guillermo Sapiro

With the wide adoption of machine learning algorithms across various application domains, there is a growing interest in the fairness properties of such algorithms.

Fairness

Cirrus: A Long-range Bi-pattern LiDAR Dataset

no code implementations5 Dec 2020 Ze Wang, Sihao Ding, Ying Li, Jonas Fenn, Sohini Roychowdhury, Andreas Wallin, Lane Martin, Scott Ryvola, Guillermo Sapiro, Qiang Qiu

Point density varies significantly across such a long range, and different scanning patterns further diversify object representation in LiDAR.

3D Object Detection Autonomous Driving +1

Instance-based Generalization in Reinforcement Learning

no code implementations NeurIPS 2020 Martin Bertran, Natalia Martinez, Mariano Phielipp, Guillermo Sapiro

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels.

Generalization Bounds

Using Text to Teach Image Retrieval

no code implementations19 Nov 2020 Haoyu Dong, Ze Wang, Qiang Qiu, Guillermo Sapiro

Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space.

Image Retrieval Semantic Similarity +1

Minimax Pareto Fairness: A Multi Objective Perspective

1 code implementation ICML 2020 Natalia Martinez, Martin Bertran, Guillermo Sapiro

In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective.

Fairness General Classification

Instance based Generalization in Reinforcement Learning

1 code implementation2 Nov 2020 Martin Bertran, Natalia Martinez, Mariano Phielipp, Guillermo Sapiro

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels.

Generalization Bounds

ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution

no code implementations4 Sep 2020 Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu

We then explicitly regularize CNN kernels by enforcing decomposed coefficients to be shared across sub-structures, while leaving each sub-structure only its own dictionary atoms, a few hundreds of parameters typically, which leads to dramatic model reductions.

Image Classification

Nested Learning For Multi-Granular Tasks

no code implementations13 Jul 2020 Raphaël Achddou, J. Matias di Martino, Guillermo Sapiro

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples.

Face Identification Object Recognition

Differential 3D Facial Recognition: Adding 3D to Your State-of-the-Art 2D Method

no code implementations3 Apr 2020 J. Matias Di Martino, Fernando Suzacq, Mauricio Delbracio, Qiang Qiu, Guillermo Sapiro

Active illumination is a prominent complement to enhance 2D face recognition and make it more robust, e. g., to spoofing attacks and low-light conditions.

3D Reconstruction Face Recognition

Fairness With Minimal Harm: A Pareto-Optimal Approach For Healthcare

no code implementations16 Nov 2019 Natalia Martinez, Martin Bertran, Guillermo Sapiro

Common fairness definitions in machine learning focus on balancing notions of disparity and utility.

Fairness

SalGaze: Personalizing Gaze Estimation Using Visual Saliency

no code implementations23 Oct 2019 Zhuoqing Chang, Matias Di Martino, Qiang Qiu, Steven Espinosa, Guillermo Sapiro

Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy.

Gaze Estimation

Range Adaptation for 3D Object Detection in LiDAR

no code implementations26 Sep 2019 Ze Wang, Sihao Ding, Ying Li, Minming Zhao, Sohini Roychowdhury, Andreas Wallin, Guillermo Sapiro, Qiang Qiu

To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds.

3D Object Detection Autonomous Driving

Scale-Equivariant Neural Networks with Decomposed Convolutional Filters

no code implementations25 Sep 2019 Wei Zhu, Qiang Qiu, Robert Calderbank, Guillermo Sapiro, Xiuyuan Cheng

Encoding the input scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many vision tasks especially when dealing with multiscale input signals.

Image Classification

Pareto Optimality in No-Harm Fairness

no code implementations25 Sep 2019 Natalia Martinez, Martin Bertran, Guillermo Sapiro

Common fairness definitions in machine learning focus on balancing various notions of disparity and utility.

Fairness

A Dictionary Approach to Domain-Invariant Learning in Deep Networks

no code implementations NeurIPS 2020 Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu

In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN).

Domain Adaptation

Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters

no code implementations24 Sep 2019 Wei Zhu, Qiang Qiu, Robert Calderbank, Guillermo Sapiro, Xiuyuan Cheng

Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs.

Image Classification Translation

Learning data-derived privacy preserving representations from information metrics

no code implementations ICLR 2019 Martin Bertran, Natalia Martinez, Afroditi Papadaki, Qiang Qiu, Miguel Rodrigues, Guillermo Sapiro

We study space-preserving transformations where the utility provider can use the same algorithm on original and sanitized data, a critical and novel attribute to help service providers accommodate varying privacy requirements with a single set of utility algorithms.

Face Recognition

Non-contact photoplethysmogram and instantaneous heart rate estimation from infrared face video

1 code implementation14 Feb 2019 Natalia Martinez, Martin Bertran, Guillermo Sapiro, Hau-Tieng Wu

One way to avoid these constraints is using infrared cameras, allowing the monitoring of iHR under low light conditions.

Heart rate estimation

Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning

no code implementations ICLR 2019 Wei Zhu, Qiang Qiu, Bao Wang, Jianfeng Lu, Guillermo Sapiro, Ingrid Daubechies

Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are imposed.

Learning to Collaborate for User-Controlled Privacy

no code implementations18 May 2018 Martin Bertran, Natalia Martinez, Afroditi Papadaki, Qiang Qiu, Miguel Rodrigues, Guillermo Sapiro

As such, users and utility providers should collaborate in data privacy, a paradigm that has not yet been developed in the privacy research community.

RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks

no code implementations ICLR 2019 Xiuyuan Cheng, Qiang Qiu, Robert Calderbank, Guillermo Sapiro

Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks.

DNN or k-NN: That is the Generalize vs. Memorize Question

no code implementations17 May 2018 Gilad Cohen, Guillermo Sapiro, Raja Giryes

Moreover, the behavior of DNNs compared to the linear classifiers SVM and LR is quite the same on the training and test data regardless of whether the network generalizes.

Liveness Detection Using Implicit 3D Features

no code implementations18 Apr 2018 J. Matias Di Martino, Qiang Qiu, Trishul Nagenalli, Guillermo Sapiro

Spoofing attacks are a threat to modern face recognition systems.

3D Reconstruction Face Recognition

Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification

1 code implementation15 Mar 2018 Albert Gong, Qiang Qiu, Guillermo Sapiro

In this paper we introduce an ensemble method for convolutional neural network (CNN), called "virtual branching," which can be implemented with nearly no additional parameters and computation on top of standard CNNs.

Person Re-Identification

DCFNet: Deep Neural Network with Decomposed Convolutional Filters

1 code implementation ICML 2018 Qiang Qiu, Xiuyuan Cheng, Robert Calderbank, Guillermo Sapiro

In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficients remain learned from data.

General Classification Image Classification

OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning

1 code implementation5 Dec 2017 José Lezama, Qiang Qiu, Pablo Musé, Guillermo Sapiro

Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification.

General Classification Metric Learning +2

ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks

no code implementations ECCV 2018 Qiang Qiu, Jose Lezama, Alex Bronstein, Guillermo Sapiro

In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees.

General Classification Image Classification +1

LDMNet: Low Dimensional Manifold Regularized Neural Networks

no code implementations CVPR 2018 Wei Zhu, Qiang Qiu, Jiaji Huang, Robert Calderbank, Guillermo Sapiro, Ingrid Daubechies

To resolve this, we propose a new framework, the Low-Dimensional-Manifold-regularized neural Network (LDMNet), which incorporates a feature regularization method that focuses on the geometry of both the input data and the output features.

Face Recognition Small Data Image Classification

Deep Video Deblurring for Hand-Held Cameras

1 code implementation CVPR 2017 Shuochen Su, Mauricio Delbracio, Jue Wang, Guillermo Sapiro, Wolfgang Heidrich, Oliver Wang

We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

Deblurring Image Deblurring +1

Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems

no code implementations23 May 2017 Jure Sokolic, Qiang Qiu, Miguel R. D. Rodrigues, Guillermo Sapiro

Confronted with this challenge, in this paper we open a new line of research, where the security, privacy, and fairness is learned and used in a closed environment.

Fairness

Deep Video Deblurring

1 code implementation25 Nov 2016 Shuochen Su, Mauricio Delbracio, Jue Wang, Guillermo Sapiro, Wolfgang Heidrich, Oliver Wang

We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

Deblurring Image Deblurring +1

Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model

no code implementations CVPR 2017 Qixiang Ye, Tianliang Zhang, Qiang Qiu, Baochang Zhang, Jie Chen, Guillermo Sapiro

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved.

Object Discovery Object Localization +2

Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding

no code implementations CVPR 2017 Jose Lezama, Qiang Qiu, Guillermo Sapiro

We observe that it is often equally effective to perform hallucination to input NIR images or low-rank embedding to output deep features for a VIS deep model for cross-spectral recognition.

Face Recognition

Probabilistic Fluorescence-Based Synapse Detection

no code implementations16 Nov 2016 Anish K. Simhal, Cecilia Aguerrebere, Forrest Collman, Joshua T. Vogelstein, Kristina D. Micheva, Richard J. Weinberg, Stephen J. Smith, Guillermo Sapiro

The present work describes new probabilistic image analysis methods for single-synapse analysis of synapse populations in both animal and human brains.

Nonnegative Matrix Underapproximation for Robust Multiple Model Fitting

no code implementations CVPR 2017 Mariano Tepper, Guillermo Sapiro

In this work, we introduce a highly efficient algorithm to address the nonnegative matrix underapproximation (NMU) problem, i. e., nonnegative matrix factorization (NMF) with an additional underapproximation constraint.

Fast L1-NMF for Multiple Parametric Model Estimation

1 code implementation18 Oct 2016 Mariano Tepper, Guillermo Sapiro

In this work we introduce a comprehensive algorithmic pipeline for multiple parametric model estimation.

Generalization Error of Invariant Classifiers

no code implementations14 Oct 2016 Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel R. D. Rodrigues

We show that whereas the generalization error of a non-invariant classifier is proportional to the complexity of the input space, the generalization error of an invariant classifier is proportional to the complexity of the base space.

Robust Large Margin Deep Neural Networks

no code implementations26 May 2016 Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel R. D. Rodrigues

The generalization error of deep neural networks via their classification margin is studied in this work.

Fundamental Limits in Multi-image Alignment

no code implementations4 Feb 2016 Cecilia Aguerrebere, Mauricio Delbracio, Alberto Bartesaghi, Guillermo Sapiro

In this work, we tackle the problem of finding the performance limits in image registration when multiple shifted and noisy observations are available.

Image Registration

GraphConnect: A Regularization Framework for Neural Networks

no code implementations21 Dec 2015 Jiaji Huang, Qiang Qiu, Robert Calderbank, Guillermo Sapiro

The new method encourages the relationships between the learned decisions to resemble a graph representing the manifold structure.

Discriminative Robust Transformation Learning

no code implementations NeurIPS 2015 Jiaji Huang, Qiang Qiu, Guillermo Sapiro, Robert Calderbank

This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of trainingsamples are available.

Geometry-aware Deep Transform

no code implementations ICCV 2015 Jiaji Huang, Qiang Qiu, Robert Calderbank, Guillermo Sapiro

Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets.

Metric Learning

Hand-held Video Deblurring via Efficient Fourier Aggregation

no code implementations17 Sep 2015 Mauricio Delbracio, Guillermo Sapiro

In this work, we present an algorithm that removes blur due to camera shake by combining information in the Fourier domain from nearby frames in a video.

Deblurring

Burst Deblurring: Removing Camera Shake Through Fourier Burst Accumulation

no code implementations CVPR 2015 Mauricio Delbracio, Guillermo Sapiro

Numerous recent approaches attempt to remove image blur due to camera shake, either with one or multiple input images, by explicitly solving an inverse and inherently ill-posed deconvolution problem.

Deblurring

Compressed Nonnegative Matrix Factorization is Fast and Accurate

1 code implementation18 May 2015 Mariano Tepper, Guillermo Sapiro

To address this, in this work we propose to use structured random compression, that is, random projections that exploit the data structure, for two NMF variants: classical and separable.

Removing Camera Shake via Weighted Fourier Burst Accumulation

no code implementations11 May 2015 Mauricio Delbracio, Guillermo Sapiro

The proposed algorithm is strikingly simple: it performs a weighted average in the Fourier domain, with weights depending on the Fourier spectrum magnitude.

Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?

no code implementations30 Apr 2015 Raja Giryes, Guillermo Sapiro, Alex M. Bronstein

Three important properties of a classification machinery are: (i) the system preserves the core information of the input data; (ii) the training examples convey information about unseen data; and (iii) the system is able to treat differently points from different classes.

Dictionary Learning General Classification +1

On the Stability of Deep Networks

no code implementations18 Dec 2014 Raja Giryes, Guillermo Sapiro, Alex M. Bronstein

In particular, we formally prove in the longer version that DNN with random Gaussian weights perform a distance-preserving embedding of the data, with a special treatment for in-class and out-of-class data.

Random Forests Can Hash

no code implementations16 Dec 2014 Qiang Qiu, Guillermo Sapiro, Alex Bronstein

Traditional random forest fails to enforce the consistency of hashes generated from each tree for the same class data, i. e., to preserve the underlying similarity, and it also lacks a principled way for code aggregation across trees.

Dissimilarity-based Sparse Subset Selection

no code implementations25 Jul 2014 Ehsan Elhamifar, Guillermo Sapiro, S. Shankar Sastry

The solution of our optimization finds representatives and the assignment of each element of the target set to each representative, hence, obtaining a clustering.

Recommendation Systems Time Series

Graph Matching: Relax at Your Own Risk

no code implementations13 May 2014 Vince Lyzinski, Donniell Fishkind, Marcelo Fiori, Joshua T. Vogelstein, Carey E. Priebe, Guillermo Sapiro

Indeed, experimental results illuminate and corroborate these theoretical findings, demonstrating that excellent results are achieved in both benchmark and real data problems by amalgamating the two approaches.

Graph Matching

A Bi-clustering Framework for Consensus Problems

no code implementations30 Apr 2014 Mariano Tepper, Guillermo Sapiro

We consider grouping as a general characterization for problems such as clustering, community detection in networks, and multiple parametric model estimation.

Community Detection

Low-Cost Compressive Sensing for Color Video and Depth

no code implementations CVPR 2014 Xin Yuan, Patrick Llull, Xuejun Liao, Jianbo Yang, Guillermo Sapiro, David J. Brady, Lawrence Carin

A simple and inexpensive (low-power and low-bandwidth) modification is made to a conventional off-the-shelf color video camera, from which we recover {multiple} color frames for each of the original measured frames, and each of the recovered frames can be focused at a different depth.

Compressive Sensing Translation

Sparse similarity-preserving hashing

no code implementations19 Dec 2013 Jonathan Masci, Alex M. Bronstein, Michael M. Bronstein, Pablo Sprechmann, Guillermo Sapiro

In recent years, a lot of attention has been devoted to efficient nearest neighbor search by means of similarity-preserving hashing.

Learning Transformations for Classification Forests

no code implementations19 Dec 2013 Qiang Qiu, Guillermo Sapiro

This work introduces a transformation-based learner model for classification forests.

General Classification

Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching

no code implementations NeurIPS 2013 Marcelo Fiori, Pablo Sprechmann, Joshua Vogelstein, Pablo Musé, Guillermo Sapiro

We also present results on multimodal graphs and applications to collaborative inference of brain connectivity from alignment-free functional magnetic resonance imaging (fMRI) data.

Graph Matching

Learning Transformations for Clustering and Classification

no code implementations9 Sep 2013 Qiang Qiu, Guillermo Sapiro

A low-rank transformation learning framework for subspace clustering and classification is here proposed.

General Classification

Domain-invariant Face Recognition using Learned Low-rank Transformation

no code implementations1 Aug 2013 Qiang Qiu, Guillermo Sapiro, Ching-Hui Chen

We present a low-rank transformation approach to compensate for face variations due to changes in visual domains, such as pose and illumination.

Face Recognition Object Recognition

Learning Robust Subspace Clustering

no code implementations1 Aug 2013 Qiang Qiu, Guillermo Sapiro

This proposed learned robust subspace clustering framework significantly enhances the performance of existing subspace clustering methods.

Video Human Segmentation using Fuzzy Object Models and its Application to Body Pose Estimation of Toddlers for Behavior Studies

no code implementations29 May 2013 Thiago V. Spina, Mariano Tepper, Amy Esler, Vassilios Morellas, Nikolaos Papanikolopoulos, Alexandre X. Falcão, Guillermo Sapiro

Video object segmentation is a challenging problem due to the presence of deformable, connected, and articulated objects, intra- and inter-object occlusions, object motion, and poor lighting.

Pose Estimation Semantic Segmentation +3

Finding Exemplars from Pairwise Dissimilarities via Simultaneous Sparse Recovery

no code implementations NeurIPS 2012 Ehsan Elhamifar, Guillermo Sapiro, René Vidal

Given pairwise dissimilarities between data points, we consider the problem of finding a subset of data points called representatives or exemplars that can efficiently describe the data collection.

Topology Constraints in Graphical Models

no code implementations NeurIPS 2012 Marcelo Fiori, Pablo Musé, Guillermo Sapiro

Graphical models are a very useful tool to describe and understand natural phenomena, from gene expression to climate change and social interactions.

Supervised Dictionary Learning

no code implementations NeurIPS 2008 Julien Mairal, Jean Ponce, Guillermo Sapiro, Andrew Zisserman, Francis R. Bach

It is now well established that sparse signal models are well suited to restoration tasks and can effectively be learned from audio, image, and video data.

Dictionary Learning General Classification +1

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