Search Results for author: David Vazquez

Found 55 papers, 32 papers with code

StarVector: Generating Scalable Vector Graphics Code from Images

no code implementations17 Dec 2023 Juan A. Rodriguez, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, David Vazquez, Christopher Pal, Marco Pedersoli

These visual tokens are pre-pended to the SVG token embeddings, and the sequence is modeled by the StarCoder model using next-token prediction, effectively learning to align the visual and code tokens.

Code Generation Vector Graphics

Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection

1 code implementation22 Aug 2023 Charles Guille-Escuret, Pierre-André Noël, Ioannis Mitliagkas, David Vazquez, Joao Monteiro

Our findings reveal that while these methods excel in detecting unknown classes, their performance is inconsistent when encountering other types of distribution shifts.

Benchmarking Out-of-Distribution Detection

GEO-Bench: Toward Foundation Models for Earth Monitoring

1 code implementation NeurIPS 2023 Alexandre Lacoste, Nils Lehmann, Pau Rodriguez, Evan David Sherwin, Hannah Kerner, Björn Lütjens, Jeremy Andrew Irvin, David Dao, Hamed Alemohammad, Alexandre Drouin, Mehmet Gunturkun, Gabriel Huang, David Vazquez, Dava Newman, Yoshua Bengio, Stefano Ermon, Xiao Xiang Zhu

Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to downstream tasks.

Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans

no code implementations2 Jun 2023 Stefania Raimondo, Christopher Pal, Xiaotian Liu, David Vazquez, Hector Palacios

We perform extensive experiments on the Action-Based Conversations Dataset (ABCD) with T5-small, base and large models, and show that such models: a) are able to more readily generalize to unseen workflows by following the provided plan, and b) are able to generalize to executing unseen actions if they are provided in the plan.

valid

FigGen: Text to Scientific Figure Generation

1 code implementation1 Jun 2023 Juan A Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez

The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art.

Language Decision Transformers with Exponential Tilt for Interactive Text Environments

no code implementations10 Feb 2023 Nicolas Gontier, Pau Rodriguez, Issam Laradji, David Vazquez, Christopher Pal

Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards.

Offline RL

Exploring validation metrics for offline model-based optimisation with diffusion models

1 code implementation19 Nov 2022 Christopher Beckham, Alexandre Piche, David Vazquez, Christopher Pal

Measuring the mean reward of generated candidates over this approximation is one such `validation metric', whereas we are interested in a more fundamental question which is finding which validation metrics correlate the most with the ground truth.

Denoising Model Selection

Flaky Performances when Pretraining on Relational Databases

no code implementations9 Nov 2022 Shengchao Liu, David Vazquez, Jian Tang, Pierre-André Noël

We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extracted from relational databases (RDBs).

Self-Supervised Learning

Implicit Offline Reinforcement Learning via Supervised Learning

no code implementations21 Oct 2022 Alexandre Piche, Rafael Pardinas, David Vazquez, Igor Mordatch, Chris Pal

Despite the benefits of using implicit models to learn robotic skills via BC, offline RL via Supervised Learning algorithms have been limited to explicit models.

Offline RL reinforcement-learning +1

OCR-VQGAN: Taming Text-within-Image Generation

2 code implementations19 Oct 2022 Juan A. Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez

To alleviate this problem, we present OCR-VQGAN, an image encoder, and decoder that leverages OCR pre-trained features to optimize a text perceptual loss, encouraging the architecture to preserve high-fidelity text and diagram structure.

Image Generation Optical Character Recognition (OCR)

Constraining Representations Yields Models That Know What They Don't Know

no code implementations30 Aug 2022 Joao Monteiro, Pau Rodriguez, Pierre-Andre Noel, Issam Laradji, David Vazquez

In the add-on case, the original neural network's inference head is completely unaffected (so its accuracy remains the same) but we now have the option to use TAC's own confidence and prediction when determining which course of action to take in an hypothetical production workflow.

Workflow Discovery from Dialogues in the Low Data Regime

1 code implementation24 May 2022 Amine El Hattami, Stefania Raimondo, Issam Laradji, David Vazquez, Pau Rodriguez, Chris Pal

We propose and evaluate an approach that conditions models on the set of possible actions, and we show that using this strategy, we can improve WD performance.

Workflow Discovery

Overcoming challenges in leveraging GANs for few-shot data augmentation

1 code implementation30 Mar 2022 Christopher Beckham, Issam Laradji, Pau Rodriguez, David Vazquez, Derek Nowrouzezahrai, Christopher Pal

In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance.

Classification Data Augmentation +1

Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark

no code implementations1 Dec 2021 Alexandre Lacoste, Evan David Sherwin, Hannah Kerner, Hamed Alemohammad, Björn Lütjens, Jeremy Irvin, David Dao, Alex Chang, Mehmet Gunturkun, Alexandre Drouin, Pau Rodriguez, David Vazquez

Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to impressive increases in generalisation for downstream tasks.

A Survey of Self-Supervised and Few-Shot Object Detection

1 code implementation27 Oct 2021 Gabriel Huang, Issam Laradji, David Vazquez, Simon Lacoste-Julien, Pau Rodriguez

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image.

Few-Shot Object Detection Instance Segmentation +3

A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images

no code implementations30 Sep 2021 Alzayat Saleh, Issam H. Laradji, Corey Lammie, David Vazquez, Carol A Flavell, Mostafa Rahimi Azghadi

US images can be used to measure abdominal muscles dimensions for the diagnosis and creation of customized treatment plans for patients with Low Back Pain (LBP), however, they are difficult to interpret.

Overcoming Label Ambiguity with Multi-label Iterated Learning

no code implementations29 Sep 2021 Sai Rajeswar Mudumba, Pau Rodriguez, Soumye Singhal, David Vazquez, Aaron Courville

This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data.

Multi-Label Learning Transfer Learning

SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction

1 code implementation21 Aug 2021 Issam Laradji, Pau Rodríguez, David Vazquez, Derek Nowrouzezahrai

In order to obtain the viewpoints for these unlabeled images, we propose to use a Siamese network that takes two images as input and outputs whether they correspond to the same viewpoint.

3D Reconstruction

Touch-based Curiosity for Sparse-Reward Tasks

1 code implementation1 Apr 2021 Sai Rajeswar, Cyril Ibrahim, Nitin Surya, Florian Golemo, David Vazquez, Aaron Courville, Pedro O. Pinheiro

Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion.

Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations

2 code implementations ICCV 2021 Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam Laradji, Laurent Charlin, David Vazquez

Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.

Attribute BIG-bench Machine Learning +2

Knowledge Hypergraph Embedding Meets Relational Algebra

1 code implementation18 Feb 2021 Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole

Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation.

hypergraph embedding Knowledge Graphs +1

Beyond Trivial Counterfactual Generations with Diverse Valuable Explanations

no code implementations1 Jan 2021 Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam H. Laradji, Laurent Charlin, David Vazquez

In computer vision applications, most methods explain models by displaying the regions in the input image that they focus on for their prediction, but it is difficult to improve models based on these explanations since they do not indicate why the model fail.

Attribute counterfactual +1

Affinity LCFCN: Learning to Segment Fish with Weak Supervision

1 code implementation6 Nov 2020 Issam Laradji, Alzayat Saleh, Pau Rodriguez, Derek Nowrouzezahrai, Mostafa Rahimi Azghadi, David Vazquez

Leading automatic approaches rely on fully-supervised segmentation models to acquire these measurements but these require collecting per-pixel labels -- also time consuming and laborious: i. e., it can take up to two minutes per fish to generate accurate segmentation labels, almost always requiring at least some manual intervention.

Segmentation

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

1 code implementation14 Sep 2020 Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.

Benchmarking Continual Learning

A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis

1 code implementation28 Aug 2020 Alzayat Saleh, Issam H. Laradji, Dmitry A. Konovalov, Michael Bradley, David Vazquez, Marcus Sheaves

The dataset consists of approximately 40 thousand images collected underwater from 20 \green{habitats in the} marine-environments of tropical Australia.

A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images

3 code implementations4 Jul 2020 Issam Laradji, Pau Rodriguez, Oscar Mañas, Keegan Lensink, Marco Law, Lironne Kurzman, William Parker, David Vazquez, Derek Nowrouzezahrai

Thus, we propose a consistency-based (CB) loss function that encourages the output predictions to be consistent with spatial transformations of the input images.

LOOC: Localize Overlapping Objects with Count Supervision

1 code implementation3 Jul 2020 Issam H. Laradji, Rafael Pardinas, Pau Rodriguez, David Vazquez

For localization, LOOC achieves a strong new baseline in the novel problem setup where only count supervision is available.

Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation

1 code implementation23 Mar 2020 Sai Rajeswar, Fahim Mannan, Florian Golemo, Jérôme Parent-Lévesque, David Vazquez, Derek Nowrouzezahrai, Aaron Courville

We propose Pix2Shape, an approach to solve this problem with four components: (i) an encoder that infers the latent 3D representation from an image, (ii) a decoder that generates an explicit 2. 5D surfel-based reconstruction of a scene from the latent code (iii) a differentiable renderer that synthesizes a 2D image from the surfel representation, and (iv) a critic network trained to discriminate between images generated by the decoder-renderer and those from a training distribution.

Slanted Stixels: A way to represent steep streets

no code implementations2 Oct 2019 Daniel Hernandez-Juarez, Lukas Schneider, Pau Cebrian, Antonio Espinosa, David Vazquez, Antonio M. Lopez, Uwe Franke, Marc Pollefeys, Juan C. Moure

This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information.

Adversarial Learning of General Transformations for Data Augmentation

no code implementations ICLR Workshop LLD 2019 Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed, Marco Pedersoli

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset.

Data Augmentation

Fourier-CPPNs for Image Synthesis

no code implementations20 Sep 2019 Mattie Tesfaldet, Xavier Snelgrove, David Vazquez

Compositional Pattern Producing Networks (CPPNs) are differentiable networks that independently map (x, y) pixel coordinates to (r, g, b) colour values.

Image Generation

Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation

1 code implementation30 Aug 2019 Lironne Kurzman, David Vazquez, Issam Laradji

We propose a Class-Based Styling method (CBS) that can map different styles for different object classes in real-time.

Object Segmentation +2

Pix2Scene: Learning Implicit 3D Representations from Images

no code implementations ICLR 2019 Sai Rajeswar, Fahim Mannan, Florian Golemo, David Vazquez, Derek Nowrouzezahrai, Aaron Courville

Modelling 3D scenes from 2D images is a long-standing problem in computer vision with implications in, e. g., simulation and robotics.

Where are the Blobs: Counting by Localization with Point Supervision

3 code implementations ECCV 2018 Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro, David Vazquez, Mark Schmidt

However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods.

Object Object Counting +1

From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example

no code implementations29 Dec 2016 Antonio M. Lopez, Jiaolong Xu, Jose L. Gomez, David Vazquez, German Ros

However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA).

Domain Adaptation

Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest

no code implementations9 Nov 2016 Azadeh S. Mozafari, David Vazquez, Mansour Jamzad, Antonio M. Lopez

Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency.

Domain Adaptation General Classification +4

The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes

no code implementations CVPR 2016 German Ros, Laura Sellart, Joanna Materzynska, David Vazquez, Antonio M. Lopez

In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations.

Autonomous Driving Segmentation +1

Hierarchical Adaptive Structural SVM for Domain Adaptation

no code implementations22 Aug 2014 Jiaolong Xu, Sebastian Ramos, David Vazquez, Antonio M. Lopez

In both cases, we show how HA-SSVM is effective in increasing the detection/recognition accuracy with respect to adaptation strategies that ignore the structure of the target data.

Domain Adaptation General Classification +5

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