AIConfPaper
← Search

Guillermo Sapiro

31 accepted papers

2025

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration

Antoine Wehenkel, Juan L. Gamella, Ozan Sener, Jens Behrmann, Guillermo Sapiro, Joern-Henrik Jacobsen +1
ICML 2025oral

Driven by steady progress in deep generative modeling, simulation-based inference (SBI) has emerged as the workhorse for inferring the parameters of stochastic simulators. However, recent work has demonstrated that model misspecification can harm SBI's reliability, preventing its adoption in importa…

Cited by 12Source ↗PDF ↗Scholar ↗
2025

SSOLE: Rethinking Orthogonal Low-rank Embedding for Self-Supervised Learning

Lun Huang, Qiang Qiu, Guillermo Sapiro
ICLR 2025poster

Self-supervised learning (SSL) aims to learn meaningful representations from unlabeled data. Orthogonal Low-rank Embedding (OLE) shows promise for SSL by enhancing intra-class similarity in a low-rank subspace and promoting inter-class dissimilarity in a high-rank subspace, making it particularly su…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Achieving Group Distributional Robustness and Minimax Group Fairness with Interpolating Classifiers

Natalia L. Martinez, Martin A. Bertran, Guillermo Sapiro
AISTATS 2024poster

Group distributional robustness optimization methods (GDRO) learn models that guarantee performance across a broad set of demographics. GDRO is often framed as a minimax game where an adversary proposes data distributions under which the model performs poorly; importance weights are used to mimic th…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks

Amirhossein Farzam, Allen Tannenbaum, Guillermo Sapiro
ICML 2024poster

Causal inference on networks faces challenges posed in part by violations of standard identification assumptions due to dependencies between treatment units. Although graph geometry fundamentally influences such dependencies, the potential of geometric tools for causal inference on networked treatme…

Cited by 1Source ↗PDF ↗Scholar ↗
2021

Blind Pareto Fairness and Subgroup Robustness

Natalia L Martinez, Martin A Bertran, Afroditi Papadaki, Miguel Rodrigues, Guillermo Sapiro
ICML 2021spotlight

Much of the work in the field of group fairness addresses disparities between predefined groups based on protected features such as gender, age, and race, which need to be available at train, and often also at test, time. These approaches are static and retrospective, since algorithms designed to pr…

Cited by 50Source ↗PDF ↗code ↗Scholar ↗
2021

Cirrus: A Long-range Bi-pattern LiDAR Dataset

Ze Wang, Sihao Ding, Ying Li, Jonas Fenn, Sohini Roychowdhury, Andreas Wallin +4
ICRA 2021poster

In this paper, we introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway driving and timely decision making. Our platform is equipped with a high-resolution video camera and a pair of LiDAR sensors with a 250-m…

Cited by 41Source ↗Scholar ↗
2020

A Dictionary Approach to Domain-Invariant Learning in Deep Networks

Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
NeurIPS 2020poster

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). By exploiting the observation that a convolutional filter can be well approximated as a linear combination o…

Cited by 11Source ↗PDF ↗Scholar ↗
2020

Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors

Gilad Cohen, Guillermo Sapiro, Raja Giryes
CVPR 2020poster

Deep neural networks (DNNs) are notorious for their vulnerability to adversarial attacks, which are small perturbations added to their input images to mislead their prediction. Detection of adversarial examples is, therefore, a fundamental requirement for robust classification frameworks. In this wo…

Cited by 178PDF ↗code ↗Scholar ↗
2020

Instance-based Generalization in Reinforcement Learning

Martin Bertran, Natalia Martinez, Mariano Phielipp, Guillermo Sapiro
NeurIPS 2020poster

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. Understanding the generalization properties of RL is one of the challenges of modern machine learning. Towards this goal…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2020

Minimax Pareto Fairness: A Multi Objective Perspective

Natalia Martinez, Martin Bertran, Guillermo Sapiro
ICML 2020poster

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. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecess…

Cited by 258Source ↗PDF ↗code ↗Scholar ↗
2019

Adversarially Learned Representations for Information Obfuscation and Inference

Martin Bertran, Natalia Martinez, Afroditi Papadaki, Qiang Qiu, Miguel Rodrigues, Galen Reeves +1
ICML 2019oral

Data collection and sharing are pervasive aspects of modern society. This process can either be voluntary, as in the case of a person taking a facial image to unlock his/her phone, or incidental, such as traffic cameras collecting videos on pedestrians. An undesirable side effect of these processes…

Cited by 78Source ↗PDF ↗code ↗Scholar ↗
2019

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

Xiuyuan Cheng, Qiang Qiu, Robert Calderbank, Guillermo Sapiro
ICLR 2019poster

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. This paper proposes to decompose the convolutional filters over joint steerable bases across the…

Cited by 50Source ↗PDF ↗Scholar ↗
2018

A Practical Guide to Multi-Image Alignment

Cecilia Aguerrebere, Mauricio Delbracio, Alberto Bartesaghi, Guillermo Sapiro
ICASSP 2018accepted

Multi - image alignment, bringing a group of images into common register, is an ubiquitous problem and the first step of many applications in a wide variety of domains. As a result, a great amount of effort is being invested in developing efficient multi-image alignment algorithms. Little has been d…

Cited by 0Source ↗Scholar ↗
2018

Classifying Pump-Probe Images of Melanocytic Lesions Using the WEYL Transform

Hyun Keun Ahn, Qiang Qiu, Edward Bosch, Andrew Thompson, Francisco E. Robles, Guillermo Sapiro +2
ICASSP 2018accepted

Diagnosis of melanoma is fraught with uncertainty, and discordance rates among physicians remain high because of the lack of a definitive criterion. Motivated by this challenge, this paper first introduces the Patch Weyl transform (PWT), a 2-dimensional variant of the Weyl transform. It then present…

Cited by 0Source ↗Scholar ↗
2018

DCFNet: Deep Neural Network with Decomposed Convolutional Filters

Qiang Qiu, Xiuyuan Cheng, Calderbank, Guillermo Sapiro
ICML 2018oral

Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. 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 e…

Cited by 80Source ↗PDF ↗code ↗Scholar ↗
2018

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

Qiang Qiu, Jose Lezama, Alex Bronstein, Guillermo Sapiro
ECCV 2018poster

In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests. A binary hash code for a data point is obtained by a set of decision trees, setting `1' for the visited tree leaf, and `0' for the rest. We propose to…

Cited by 8Source ↗PDF ↗Scholar ↗
2018

LDMNet: Low Dimensional Manifold Regularized Neural Networks

Wei Zhu, Qiang Qiu, Jiaji Huang, Robert Calderbank, Guillermo Sapiro, Ingrid Daubechies
CVPR 2018poster

Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing overfitting are data-independent. Data-dependent regularizations are…

Cited by 53Source ↗PDF ↗Scholar ↗
2018

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

José Lezama, Qiang Qiu, Pablo Musé, Guillermo Sapiro
CVPR 2018poster

Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep representations. To simultaneously achieve these two goals, d…

Cited by 102Source ↗PDF ↗code ↗Scholar ↗
2018

The Learned Inexact Project Gradient Descent Algorithm

Raja Giryes, Yonina C. Eldar, Alexander M. Bronstein, Guillermo Sapiro
ICASSP 2018accepted

Accelerating iterative algorithms for solving inverse problems using neural networks have become a very popular strategy in the recent years. In this work, we propose a theoretical analysis that may provide an explanation for its success. Our theory relies on the usage of inexact projections with th…

Cited by 0Source ↗Scholar ↗
2017

Deep Video Deblurring for Hand-Held Cameras

Shuochen Su, Mauricio Delbracio, Jue Wang, Guillermo Sapiro, Wolfgang Heidrich, Oliver Wang
CVPR 2017spotlight

Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of near…

Cited by 711PDF ↗Scholar ↗
2017

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

Jose Lezama, Qiang Qiu, Guillermo Sapiro
CVPR 2017poster

Surveillance cameras today often capture NIR (near infrared) images in low-light environments. However, most face datasets accessible for training and verification are only collected in the VIS (visible light) spectrum. It remains a challenging problem to match NIR to VIS face images due to the diff…

Cited by 169PDF ↗Scholar ↗
2017

Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model

Qixiang Ye, Tianliang Zhang, Wei Ke, Qiang Qiu, Jie Chen, Guillermo Sapiro +1
CVPR 2017poster

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedur…

Cited by 41PDF ↗Scholar ↗
2015

Alignment with intra-class structure can improve classification

Jiaji Huang, Qiang Qiu, A. Robert Calderbank, Miguel R. D. Rodrigues, Guillermo Sapiro
ICASSP 2015accepted

High dimensional data is modeled using low-rank subspaces, and the probability of misclassification is expressed in terms of the principal angles between subspaces. The form taken by this expression motivates the design of a new feature extraction method that enlarges inter-class separation, while p…

Cited by 0Source ↗Scholar ↗