301 results on '"Romero, Adriana"'
Search Results
2. Aqueous phase recycling: impact on microalgal lipid accumulation and biomass quality
- Author
-
Ramírez-Romero, Adriana, da Costa Magalhães, Bruno, Matricon, Lucie, Sassi, Jean-François, Steyer, Jean-Philippe, and Delrue, Florian
- Published
- 2024
- Full Text
- View/download PDF
3. Active 3D Shape Reconstruction from Vision and Touch
- Author
-
Smith, Edward J., Meger, David, Pineda, Luis, Calandra, Roberto, Malik, Jitendra, Romero, Adriana, and Drozdzal, Michal
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Robotics - Abstract
Humans build 3D understandings of the world through active object exploration, using jointly their senses of vision and touch. However, in 3D shape reconstruction, most recent progress has relied on static datasets of limited sensory data such as RGB images, depth maps or haptic readings, leaving the active exploration of the shape largely unexplored. Inactive touch sensing for 3D reconstruction, the goal is to actively select the tactile readings that maximize the improvement in shape reconstruction accuracy. However, the development of deep learning-based active touch models is largely limited by the lack of frameworks for shape exploration. In this paper, we focus on this problem and introduce a system composed of: 1) a haptic simulator leveraging high spatial resolution vision-based tactile sensors for active touching of 3D objects; 2)a mesh-based 3D shape reconstruction model that relies on tactile or visuotactile signals; and 3) a set of data-driven solutions with either tactile or visuotactile priors to guide the shape exploration. Our framework enables the development of the first fully data-driven solutions to active touch on top of learned models for object understanding. Our experiments show the benefits of such solutions in the task of 3D shape understanding where our models consistently outperform natural baselines. We provide our framework as a tool to foster future research in this direction.
- Published
- 2021
4. A novel approach for direct detection of the IGH::CRLF2 gene fusion by fluorescent in situ hybridization
- Author
-
González-Arreola, Rosa María, García-Romero, Adriana, Magaña-Torres, María Teresa, and González-García, Juan Ramón
- Published
- 2023
- Full Text
- View/download PDF
5. Active MR k-space Sampling with Reinforcement Learning
- Author
-
Pineda, Luis, Basu, Sumana, Romero, Adriana, Calandra, Roberto, and Drozdzal, Michal
- Subjects
Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Deep learning approaches have recently shown great promise in accelerating magnetic resonance image (MRI) acquisition. The majority of existing work have focused on designing better reconstruction models given a pre-determined acquisition trajectory, ignoring the question of trajectory optimization. In this paper, we focus on learning acquisition trajectories given a fixed image reconstruction model. We formulate the problem as a sequential decision process and propose the use of reinforcement learning to solve it. Experiments on a large scale public MRI dataset of knees show that our proposed models significantly outperform the state-of-the-art in active MRI acquisition, over a large range of acceleration factors., Comment: Presented at the 23rd International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2020
- Published
- 2020
- Full Text
- View/download PDF
6. 3D Shape Reconstruction from Vision and Touch
- Author
-
Smith, Edward J., Calandra, Roberto, Romero, Adriana, Gkioxari, Georgia, Meger, David, Malik, Jitendra, and Drozdzal, Michal
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Robotics - Abstract
When a toddler is presented a new toy, their instinctual behaviour is to pick it upand inspect it with their hand and eyes in tandem, clearly searching over its surface to properly understand what they are playing with. At any instance here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to multi-modal shape understanding which encourages a similar fusion vision and touch information.To do so, we introduce a dataset of simulated touch and vision signals from the interaction between a robotic hand and a large array of 3D objects. Our results show that (1) leveraging both vision and touch signals consistently improves single-modality baselines; (2) our approach outperforms alternative modality fusion methods and strongly benefits from the proposed chart-based structure; (3) there construction quality increases with the number of grasps provided; and (4) the touch information not only enhances the reconstruction at the touch site but also extrapolates to its local neighborhood., Comment: Accepted at Neurips 2020
- Published
- 2020
7. Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver
- Author
-
Sagun, Levent, Gulcehre, Caglar, Romero, Adriana, Rostamzadeh, Negar, and Mannelli, Stefano Sarao
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
Science meets Engineering in Deep Learning took place in Vancouver as part of the Workshop section of NeurIPS 2019. As organizers of the workshop, we created the following report in an attempt to isolate emerging topics and recurring themes that have been presented throughout the event. Deep learning can still be a complex mix of art and engineering despite its tremendous success in recent years. The workshop aimed at gathering people across the board to address seemingly contrasting challenges in the problems they are working on. As part of the call for the workshop, particular attention has been given to the interdependence of architecture, data, and optimization that gives rise to an enormous landscape of design and performance intricacies that are not well-understood. This year, our goal was to emphasize the following directions in our community: (i) identify obstacles in the way to better models and algorithms; (ii) identify the general trends from which we would like to build scientific and potentially theoretical understanding; and (iii) the rigorous design of scientific experiments and experimental protocols whose purpose is to resolve and pinpoint the origin of mysteries while ensuring reproducibility and robustness of conclusions. In the event, these topics emerged and were broadly discussed, matching our expectations and paving the way for new studies in these directions. While we acknowledge that the text is naturally biased as it comes through our lens, here we present an attempt to do a fair job of highlighting the outcome of the workshop., Comment: Report of NeurIPS 2019 workshop SEDL
- Published
- 2020
8. Learning to adapt class-specific features across domains for semantic segmentation
- Author
-
Menta, Mikel, Romero, Adriana, and van de Weijer, Joost
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any training annotations in this domain. The great majority of existing domain adaptation models rely on image translation networks, which often contain a huge amount of domain-specific parameters. Additionally, the feature adaptation step often happens globally, at a coarse level, hindering its applicability to tasks such as semantic segmentation, where details are of crucial importance to provide sharp results. In this thesis, we present a novel architecture, which learns to adapt features across domains by taking into account per class information. To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks. Moreover, following recent advances in image translation, we adopt the recently introduced StarGAN architecture as image translation backbone, since it is able to perform translations across multiple domains by means of a single generator network. Preliminary results on a segmentation task designed to assess the effectiveness of the proposed approach highlight the potential of the model, improving upon strong baselines and alternative designs., Comment: Master thesis dissertation for the Master in Computer Vision (Barcelona). 11 pages main article and 3 pages appendices. Code available
- Published
- 2020
9. Polymer/clay nanocomposite hydrogels with anisotropic properties
- Author
-
Sierra Romero, Adriana, Chen, Biqiong, and Falzon, Brian
- Subjects
Nanocomposite ,polymer ,hydrogel ,clay ,magnetism - Abstract
The use of magnetic fields has the potential to tailor the orientation and distribution of dispersed particles within polymer composites to create materials with anisotropic properties. However, limited literature exists on anisotropic nanocomposite hydrogels prepared under low magnetic fields, which are of interest for various soft and wet applications. This research reports polyacrylamide/montmorillonite-iron oxide (PAAm/MMT-IO), and poly(N-isopropylacrylamide)/MMT-IO (PNIPAM/MMT-IO) nanocomposite hydrogels prepared via low magnetic fields showing anisotropic mechanical properties. The magnetic field was studied as the parameter that produces anisotropy by controlling the orientation and distribution of the dispersed phase. MMT-IO nanohybrids at a 2:1 clay to magnetite weight ratio showed suitable magnetic properties and surface characteristics to be used in the preparation of PAAm/MMT-IO and PNIPAM/MMT-IO nanocomposite hydrogels. These materials showed swelling ratios that depended on the nanohybrid content, porous morphology with nanohybrid particles distributed along the applied magnetic field and enhanced Young's modulus, ultimate tensile strength, strain at break and toughness compared to pristine polymer hydrogel. The magnetic field was found to produce anisotropy, with superior mechanical properties along the direction of a 20 mT magnetic field produced by a couple of N35 Neodymium magnets and reduced properties on the transverse direction, compared to samples prepared in absence of a magnetic field. The Young's modulus was estimated through the Halpin-Tsai and Mori-Tanaka micromechanical models, which had not been applied for this kind of materials. The potential of PNIPAM/MMT-IO nanocomposite hydrogels was demonstrated through the design and fabrication of self-shaping multilayer structures that displayed complex deformations when subjected to a change in temperature due to their anisotropy and smart behaviour. The development of these anisotropic nanocomposite hydrogels could be useful in fields such as soft robotics and mechanobiology, where controlled deformations are desirable within a wet medium.
- Published
- 2021
10. On the Evaluation of Conditional GANs
- Author
-
DeVries, Terrance, Romero, Adriana, Pineda, Luis, Taylor, Graham W., and Drozdzal, Michal
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning ,Electrical Engineering and Systems Science - Image and Video Processing ,Statistics - Machine Learning - Abstract
Conditional Generative Adversarial Networks (cGANs) are finding increasingly widespread use in many application domains. Despite outstanding progress, quantitative evaluation of such models often involves multiple distinct metrics to assess different desirable properties, such as image quality, conditional consistency, and intra-conditioning diversity. In this setting, model benchmarking becomes a challenge, as each metric may indicate a different "best" model. In this paper, we propose the Frechet Joint Distance (FJD), which is defined as the Frechet distance between joint distributions of images and conditioning, allowing it to implicitly capture the aforementioned properties in a single metric. We conduct proof-of-concept experiments on a controllable synthetic dataset, which consistently highlight the benefits of FJD when compared to currently established metrics. Moreover, we use the newly introduced metric to compare existing cGAN-based models for a variety of conditioning modalities (e.g. class labels, object masks, bounding boxes, images, and text captions). We show that FJD can be used as a promising single metric for cGAN benchmarking and model selection. Code can be found at https://github.com/facebookresearch/fjd.
- Published
- 2019
11. Elucidating image-to-set prediction: An analysis of models, losses and datasets
- Author
-
Pineda, Luis, Salvador, Amaia, Drozdzal, Michal, and Romero, Adriana
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
In this paper, we identify an important reproducibility challenge in the image-to-set prediction literature that impedes proper comparisons among published methods, namely, researchers use different evaluation protocols to assess their contributions. To alleviate this issue, we introduce an image-to-set prediction benchmark suite built on top of five public datasets of increasing task complexity that are suitable for multi-label classification (VOC, COCO, NUS-WIDE, ADE20k and Recipe1M). Using the benchmark, we provide an in-depth analysis where we study the key components of current models, namely the choice of the image representation backbone as well as the set predictor design. Our results show that (1) exploiting better image representation backbones leads to higher performance boosts than enhancing set predictors, and (2) modeling both the label co-occurrences and ordering has a slight positive impact in terms of performance, whereas explicit cardinality prediction only helps when training on complex datasets, such as Recipe1M. To facilitate future image-to-set prediction research, we make the code, best models and dataset splits publicly available at: https://github.com/facebookresearch/image-to-set.
- Published
- 2019
12. Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
- Author
-
Zhang, Zizhao, Romero, Adriana, Muckley, Matthew J., Vincent, Pascal, Yang, Lin, and Drozdzal, Michal
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
The goal of MRI reconstruction is to restore a high fidelity image from partially observed measurements. This partial view naturally induces reconstruction uncertainty that can only be reduced by acquiring additional measurements. In this paper, we present a novel method for MRI reconstruction that, at inference time, dynamically selects the measurements to take and iteratively refines the prediction in order to best reduce the reconstruction error and, thus, its uncertainty. We validate our method on a large scale knee MRI dataset, as well as on ImageNet. Results show that (1) our system successfully outperforms active acquisition baselines; (2) our uncertainty estimates correlate with error maps; and (3) our ResNet-based architecture surpasses standard pixel-to-pixel models in the task of MRI reconstruction. The proposed method not only shows high-quality reconstructions but also paves the road towards more applicable solutions for accelerating MRI.
- Published
- 2019
13. GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
- Author
-
Smith, Edward J., Fujimoto, Scott, Romero, Adriana, and Meger, David
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to compromises with respect to performance or resolution. In this paper, we argue that the graph representation of geometric objects allows for additional structure, which should be leveraged for enhanced reconstruction. Thus, we propose a system which properly benefits from the advantages of the geometric structure of graph encoded objects by introducing (1) a graph convolutional update preserving vertex information; (2) an adaptive splitting heuristic allowing detail to emerge; and (3) a training objective operating both on the local surfaces defined by vertices as well as the global structure defined by the mesh. Our proposed method is evaluated on the task of 3D object reconstruction from images with the ShapeNet dataset, where we demonstrate state of the art performance, both visually and numerically, while having far smaller space requirements by generating adaptive meshes, Comment: 18 pages
- Published
- 2019
14. Inverse Cooking: Recipe Generation from Food Images
- Author
-
Salvador, Amaia, Drozdzal, Michal, Giro-i-Nieto, Xavier, and Romero, Adriana
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
People enjoy food photography because they appreciate food. Behind each meal there is a story described in a complex recipe and, unfortunately, by simply looking at a food image we do not have access to its preparation process. Therefore, in this paper we introduce an inverse cooking system that recreates cooking recipes given food images. Our system predicts ingredients as sets by means of a novel architecture, modeling their dependencies without imposing any order, and then generates cooking instructions by attending to both image and its inferred ingredients simultaneously. We extensively evaluate the whole system on the large-scale Recipe1M dataset and show that (1) we improve performance w.r.t. previous baselines for ingredient prediction; (2) we are able to obtain high quality recipes by leveraging both image and ingredients; (3) our system is able to produce more compelling recipes than retrieval-based approaches according to human judgment. We make code and models publicly available., Comment: CVPR 2019
- Published
- 2018
15. fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- Author
-
Zbontar, Jure, Knoll, Florian, Sriram, Anuroop, Murrell, Tullie, Huang, Zhengnan, Muckley, Matthew J., Defazio, Aaron, Stern, Ruben, Johnson, Patricia, Bruno, Mary, Parente, Marc, Geras, Krzysztof J., Katsnelson, Joe, Chandarana, Hersh, Zhang, Zizhao, Drozdzal, Michal, Romero, Adriana, Rabbat, Michael, Vincent, Pascal, Yakubova, Nafissa, Pinkerton, James, Wang, Duo, Owens, Erich, Zitnick, C. Lawrence, Recht, Michael P., Sodickson, Daniel K., and Lui, Yvonne W.
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning ,Electrical Engineering and Systems Science - Signal Processing ,Physics - Medical Physics ,Statistics - Machine Learning - Abstract
Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively slow or expensive. We introduce the fastMRI dataset, a large-scale collection of both raw MR measurements and clinical MR images, that can be used for training and evaluation of machine-learning approaches to MR image reconstruction. By introducing standardized evaluation criteria and a freely-accessible dataset, our goal is to help the community make rapid advances in the state of the art for MR image reconstruction. We also provide a self-contained introduction to MRI for machine learning researchers with no medical imaging background., Comment: 35 pages, 10 figures
- Published
- 2018
16. Microalgae adaptation as a strategy to recycle the aqueous phase from hydrothermal liquefaction
- Author
-
Ramírez-Romero, Adriana, Martin, Marion, Boyer, Alana, Bolzoni, Romain, Matricon, Lucie, Sassi, Jean-François, Steyer, Jean-Philippe, and Delrue, Florian
- Published
- 2023
- Full Text
- View/download PDF
17. Women Becoming Social Justice Leaders with an Inclusive Viewin Costa Rica, Mexico, and Spain
- Author
-
Slater, Charles L., Gorosave, Gema Lopez, Silva, Patricia, Torres, Nancy, Romero, Adriana, and Antúnez, Serafín
- Abstract
This study looks at three female school directors in Costa Rica, Mexico, and Spain who worked under challenging conditions to establish social justice. We were particularly interest in how they learned to become social justice leaders. Qualitative interviews were used to hear directly from the school directors about their experiences. Transcripts were analyzed for common themes. The commitment of these directors to social justice came from early family experiences that gave them strength and core values. They met adversity in young adulthood which reinforced their commitment to inclusive leadership.
- Published
- 2017
18. On the iterative refinement of densely connected representation levels for semantic segmentation
- Author
-
Casanova, Arantxa, Cucurull, Guillem, Drozdzal, Michal, Romero, Adriana, and Bengio, Yoshua
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segmentation architectures, receptive field enlargement operations that change the representation level are interleaved among residual networks. This allows the model to exploit the benefits of both residual and dense connectivity patterns, namely: gradient flow, iterative refinement of representations, multi-scale feature combination and deep supervision. In order to highlight the potential of our model, we test it on the challenging CamVid urban scene understanding benchmark and make the following observations: 1) downsampling operations outperform dilations when the model is trained from scratch, 2) dilations are useful during the finetuning step of the model, 3) coarser representations require less refinement steps, and 4) ResNets (by model construction) are good regularizers, since they can reduce the model capacity when needed. Finally, we compare our architecture to alternative methods and report state-of-the-art result on the Camvid dataset, with at least twice fewer parameters.
- Published
- 2018
19. Graph Attention Networks
- Author
-
Veličković, Petar, Cucurull, Guillem, Casanova, Arantxa, Romero, Adriana, Liò, Pietro, and Bengio, Yoshua
- Subjects
Statistics - Machine Learning ,Computer Science - Artificial Intelligence ,Computer Science - Learning ,Computer Science - Social and Information Networks - Abstract
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training)., Comment: To appear at ICLR 2018. 12 pages, 2 figures
- Published
- 2017
20. Introduction and Acknowledgments
- Author
-
S.V. Cantor, Sarah, Di Blasio, Federica, and Guarro Romero, Adriana
- Abstract
Introduction and Acknowledgments
- Published
- 2019
21. Image Segmentation by Iterative Inference from Conditional Score Estimation
- Author
-
Romero, Adriana, Drozdzal, Michal, Erraqabi, Akram, Jégou, Simon, and Bengio, Yoshua
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Inspired by the combination of feedforward and iterative computations in the virtual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of a joint distribution, we propose a novel approach to iterative inference for capturing and exploiting the complex joint distribution of output variables conditioned on some input variables. This approach is applied to image pixel-wise segmentation, with the estimated conditional score used to perform gradient ascent towards a mode of the estimated conditional distribution. This extends previous work on score estimation by denoising autoencoders to the case of a conditional distribution, with a novel use of a corrupted feedforward predictor replacing Gaussian corruption. An advantage of this approach over more classical ways to perform iterative inference for structured outputs, like conditional random fields (CRFs), is that it is not any more necessary to define an explicit energy function linking the output variables. To keep computations tractable, such energy function parametrizations are typically fairly constrained, involving only a few neighbors of each of the output variables in each clique. We experimentally find that the proposed iterative inference from conditional score estimation by conditional denoising autoencoders performs better than comparable models based on CRFs or those not using any explicit modeling of the conditional joint distribution of outputs.
- Published
- 2017
22. Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
- Author
-
Drozdzal, Michal, Chartrand, Gabriel, Vorontsov, Eugene, Di Jorio, Lisa, Tang, An, Romero, Adriana, Bengio, Yoshua, Pal, Chris, and Kadoury, Samuel
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Networks (FC-ResNets). We propose and examine a design that takes particular advantage of recent advances in the understanding of both Convolutional Neural Networks as well as ResNets. Our approach focuses upon the importance of a trainable pre-processing when using FC-ResNets and we show that a low-capacity FCN model can serve as a pre-processor to normalize medical input data. In our image segmentation pipeline, we use FCNs to obtain normalized images, which are then iteratively refined by means of a FC-ResNet to generate a segmentation prediction. As in other fully convolutional approaches, our pipeline can be used off-the-shelf on different image modalities. We show that using this pipeline, we exhibit state-of-the-art performance on the challenging Electron Microscopy benchmark, when compared to other 2D methods. We improve segmentation results on CT images of liver lesions, when contrasting with standard FCN methods. Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods. The obtained results illustrate the strong potential and versatility of the pipeline by achieving highly accurate results on multi-modality images from different anatomical regions and organs.
- Published
- 2017
23. A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images
- Author
-
Vázquez, David, Bernal, Jorge, Sánchez, F. Javier, Fernández-Esparrach, Gloria, López, Antonio M., Romero, Adriana, Drozdzal, Michal, and Courville, Aaron
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss-rate and inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing Decision Support Systems (DSS) aiming to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. We provide new baselines on this dataset by training standard fully convolutional networks (FCN) for semantic segmentation and significantly outperforming, without any further post-processing, prior results in endoluminal scene segmentation.
- Published
- 2016
24. Diet Networks: Thin Parameters for Fat Genomics
- Author
-
Romero, Adriana, Carrier, Pierre Luc, Erraqabi, Akram, Sylvain, Tristan, Auvolat, Alex, Dejoie, Etienne, Legault, Marc-André, Dubé, Marie-Pierre, Hussin, Julie G., and Bengio, Yoshua
- Subjects
Computer Science - Learning ,Statistics - Machine Learning - Abstract
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer: each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.
- Published
- 2016
25. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
- Author
-
Jégou, Simon, Drozdzal, Michal, Vazquez, David, Romero, Adriana, and Bengio, Yoshua
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions. Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train. In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets. Code to reproduce the experiments is available here : https://github.com/SimJeg/FC-DenseNet/blob/master/train.py
- Published
- 2016
26. The Five Pillars of Sales Coaching: Help sales managers become successful coaches with these best practices
- Author
-
Romero, Adriana
- Subjects
Employee trainers -- Methods -- Practice ,Best practices ,Sales managers -- Training ,Business ,Education ,Human resources and labor relations - Abstract
Allow me to paint a scenario: It is March 10, 2022, and you--the sales enabler--are resting after an intense start of the year filled with a virtual sales kickoff and a couple of certifications for the sellers. You have worked hard, structured the sessions, made them entertaining, and received some good initial indicators that the sessions were successful., And then, as you are going over your to-do list that seems to grow by the minute, the head of sales sends you a message: 'Can you help the managers [...]
- Published
- 2022
27. Hygrothermal properties of soil–cement construction materials
- Author
-
Costantini Romero, Adriana Belén, Francisca, Franco Matias, and Giomi, Ignacio
- Published
- 2021
- Full Text
- View/download PDF
28. Huertos en instituciones de educación superior. Relatos y experiencias desde México
- Author
-
Fontalvo Buelvas, Juan Camilo, additional, De la Cruz Elizondo, Yadeneyro, additional, Castro Martínez, Oswaldo Rahmses, additional, Ferguson, Bruce Gordon, additional, Morales, Helda Eleonora de Guadalupe, additional, Caballero Roque, Adriana, additional, Bohnel Nava, Astrid Laura, additional, Contreras Cortés, Leonardo Ernesto Ulises, additional, Ori Orlansino, Miranda, additional, Gutiérrez Navarro, Alonso, additional, Rivero Romero, Alexis Daniela, additional, Moreno Calles, Ana Isabel, additional, Ibargüen Ramón, Gloria del Rocío, additional, Ortega Meza, Daniela, additional, García, Saúl Alejandro, additional, Arroyo Cossío, Arturo Julián, additional, Valenzuela Herrera, Gilberto, additional, Arciniega Galaviz, Marco Arturo, additional, Flores Peredo, Rafael, additional, Rivera Marín, Linda Esmeralda, additional, Hernández Villarreal, Adrián Elías, additional, De las Salas Carrillo, Karen Patricia, additional, Peña Cheng, Lourdes Magdalena, additional, Hernández Huerta, Jared, additional, Hernández Rodríguez, Ofelia Adriana, additional, Gutiérrez García, Georgina, additional, Ruiz Gadea, Adriana, additional, Sántiz García, José Ignacio, additional, Rubio Delgado, Laura, additional, Junghans, Christiane Renate, additional, Hernández Corzo, Claudia, additional, Reyes Solares, Jerónimo, additional, Pérez Hernández, Amparo Guadalupe, additional, Limón Aguirre, Cecilia Guadalupe, additional, Valdivia Romero, Nadia Jocelyn, additional, Ruiz González, Rosey Obet, additional, Victorino Ramírez, Liberio, additional, Pérez Quezada, Pablo Hiram, additional, Trejo Álvarez, Ana Isabel, additional, Mondragón Padilla, Adriana, additional, Ruiz Morales, Mariana, additional, Mehner Karam, Patricia, additional, Mora van Cauwelaert, Emilio, additional, Moreno Mijares, Julia, additional, Lara García, Tania, additional, Hernández Hernández, Blanca Estela, additional, Benítez Keinrad, Mariana, additional, Alonso Fernández, Cristina, additional, Martínez Villalba, Ana Yésica, additional, Camou Guerrero, Andrés, additional, Gutiérrez Molina, Cristhian, additional, Melo Pérez, Georgina, additional, Mendoza Cruz, Yesenia, additional, Sánchez Trejo, Edith Carmina, additional, Herrera Peralta, Delfino Israel, additional, Castañeda Huerta, Elizabeth, additional, Avendaño Ruiz, Belem Dolores, additional, Chávez Quiroz, Raúl, additional, Cañedo Villarreal, Roberto, additional, Valdez Martínez, David, additional, Ávila Díaz, Jeován Alberto, additional, Hernández Villarreal, Roberto Iván, additional, García Carmona, José Benito, additional, Torres Romero, Adriana Isela, additional, Escobar Cisneros, Adla Evelyn, additional, Pérez Garcés, Ranulfo, additional, and Yurugi López, Yun Federico, additional
- Published
- 2024
- Full Text
- View/download PDF
29. Resolving phytosterols in microalgae using offline two-dimensional reversed phase liquid chromatography-supercritical fluid chromatography coupled with quadrupole time-of-flight mass spectrometry
- Author
-
Batteau, Magali, primary, Bouju, Elodie, additional, Ramirez-Romero, Adriana, additional, Nuccio, Sylvie, additional, De Vaumas, René, additional, Delrue, Florian, additional, and Faure, Karine, additional
- Published
- 2024
- Full Text
- View/download PDF
30. Theano: A Python framework for fast computation of mathematical expressions
- Author
-
The Theano Development Team, Al-Rfou, Rami, Alain, Guillaume, Almahairi, Amjad, Angermueller, Christof, Bahdanau, Dzmitry, Ballas, Nicolas, Bastien, Frédéric, Bayer, Justin, Belikov, Anatoly, Belopolsky, Alexander, Bengio, Yoshua, Bergeron, Arnaud, Bergstra, James, Bisson, Valentin, Snyder, Josh Bleecher, Bouchard, Nicolas, Boulanger-Lewandowski, Nicolas, Bouthillier, Xavier, de Brébisson, Alexandre, Breuleux, Olivier, Carrier, Pierre-Luc, Cho, Kyunghyun, Chorowski, Jan, Christiano, Paul, Cooijmans, Tim, Côté, Marc-Alexandre, Côté, Myriam, Courville, Aaron, Dauphin, Yann N., Delalleau, Olivier, Demouth, Julien, Desjardins, Guillaume, Dieleman, Sander, Dinh, Laurent, Ducoffe, Mélanie, Dumoulin, Vincent, Kahou, Samira Ebrahimi, Erhan, Dumitru, Fan, Ziye, Firat, Orhan, Germain, Mathieu, Glorot, Xavier, Goodfellow, Ian, Graham, Matt, Gulcehre, Caglar, Hamel, Philippe, Harlouchet, Iban, Heng, Jean-Philippe, Hidasi, Balázs, Honari, Sina, Jain, Arjun, Jean, Sébastien, Jia, Kai, Korobov, Mikhail, Kulkarni, Vivek, Lamb, Alex, Lamblin, Pascal, Larsen, Eric, Laurent, César, Lee, Sean, Lefrancois, Simon, Lemieux, Simon, Léonard, Nicholas, Lin, Zhouhan, Livezey, Jesse A., Lorenz, Cory, Lowin, Jeremiah, Ma, Qianli, Manzagol, Pierre-Antoine, Mastropietro, Olivier, McGibbon, Robert T., Memisevic, Roland, van Merriënboer, Bart, Michalski, Vincent, Mirza, Mehdi, Orlandi, Alberto, Pal, Christopher, Pascanu, Razvan, Pezeshki, Mohammad, Raffel, Colin, Renshaw, Daniel, Rocklin, Matthew, Romero, Adriana, Roth, Markus, Sadowski, Peter, Salvatier, John, Savard, François, Schlüter, Jan, Schulman, John, Schwartz, Gabriel, Serban, Iulian Vlad, Serdyuk, Dmitriy, Shabanian, Samira, Simon, Étienne, Spieckermann, Sigurd, Subramanyam, S. Ramana, Sygnowski, Jakub, Tanguay, Jérémie, van Tulder, Gijs, Turian, Joseph, Urban, Sebastian, Vincent, Pascal, Visin, Francesco, de Vries, Harm, Warde-Farley, David, Webb, Dustin J., Willson, Matthew, Xu, Kelvin, Xue, Lijun, Yao, Li, Zhang, Saizheng, and Zhang, Ying
- Subjects
Computer Science - Symbolic Computation ,Computer Science - Learning ,Computer Science - Mathematical Software - Abstract
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it., Comment: 19 pages, 5 figures
- Published
- 2016
31. Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
- Author
-
Romero, Adriana, Gatta, Carlo, and Camps-Valls, Gustau
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyper-spectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layer-wise unsupervised pre-training coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution (VHR), or land-cover classification from multi- and hyper-spectral images. The proposed algorithm clearly outperforms standard Principal Component Analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels, and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single layers variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.
- Published
- 2015
- Full Text
- View/download PDF
32. ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
- Author
-
Visin, Francesco, Ciccone, Marco, Romero, Adriana, Kastner, Kyle, Cho, Kyunghyun, Bengio, Yoshua, Matteucci, Matteo, and Courville, Aaron
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Learning - Abstract
We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally and vertically in both directions, encoding patches or activations, and providing relevant global information. Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features. Upsampling layers follow ReNet layers to recover the original image resolution in the final predictions. The proposed ReSeg architecture is efficient, flexible and suitable for a variety of semantic segmentation tasks. We evaluate ReSeg on several widely-used semantic segmentation datasets: Weizmann Horse, Oxford Flower, and CamVid; achieving state-of-the-art performance. Results show that ReSeg can act as a suitable architecture for semantic segmentation tasks, and may have further applications in other structured prediction problems. The source code and model hyperparameters are available on https://github.com/fvisin/reseg., Comment: In CVPR Deep Vision Workshop, 2016
- Published
- 2015
33. FitNets: Hints for Thin Deep Nets
- Author
-
Romero, Adriana, Ballas, Nicolas, Kahou, Samira Ebrahimi, Chassang, Antoine, Gatta, Carlo, and Bengio, Yoshua
- Subjects
Computer Science - Learning ,Computer Science - Neural and Evolutionary Computing - Abstract
While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student. Because the student intermediate hidden layer will generally be smaller than the teacher's intermediate hidden layer, additional parameters are introduced to map the student hidden layer to the prediction of the teacher hidden layer. This allows one to train deeper students that can generalize better or run faster, a trade-off that is controlled by the chosen student capacity. For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.
- Published
- 2014
34. Early Prediction of Alzheimer’s Disease Progression Using Variational Autoencoders
- Author
-
Basu, Sumana, Wagstyl, Konrad, Zandifar, Azar, Collins, Louis, Romero, Adriana, Precup, Doina, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Shen, Dinggang, editor, Liu, Tianming, editor, Peters, Terry M., editor, Staib, Lawrence H., editor, Essert, Caroline, editor, Zhou, Sean, editor, Yap, Pew-Thian, editor, and Khan, Ali, editor
- Published
- 2019
- Full Text
- View/download PDF
35. Inside Cover: A reversible water‐based electrostatic adhesive
- Author
-
Sierra‐Romero, Adriana, primary, Novakovic, Katarina, additional, and Geoghegan, Mark, additional
- Published
- 2023
- Full Text
- View/download PDF
36. Modelo productivo para el cultivo de yopo (Mimosa trianae Benth) en el departamento del Meta
- Author
-
Correa Pinilla, Diana Elisa, primary, Gutiérrez Vanegas, Albert Julesmar, additional, Moreno Barragán, Jessica, additional, Castañeda Garzón, Sandra Liliana, additional, Molina Romero, Adriana María, additional, López Hernández, Ferney Giovanny, additional, Camargo Tamayo, Hebert, additional, Zuluaga Peláez, Jhon Jairo, additional, Campos Pinzón, Juan Carlos, additional, and Ostos Triana, Manuel Eduardo, additional
- Published
- 2023
- Full Text
- View/download PDF
37. A reversible water‐based electrostatic adhesive
- Author
-
Sierra‐Romero, Adriana, primary, Novakovic, Katarina, additional, and Geoghegan, Mark, additional
- Published
- 2023
- Full Text
- View/download PDF
38. Narrative Friendships in Elisabetta Rasy's "Posillipo" and Elena Ferrante's Neapolitan Novels
- Author
-
Romero, Adriana Guarro
- Published
- 2019
- Full Text
- View/download PDF
39. Manual de costos y análisis financiero para el sistema productivo de ganadería de ceba en la Orinoquía colombiana
- Author
-
Molina Romero, Adriana María, primary, Flórez Díaz, Hernando, additional, and Ostos Triana, Manuel Eduardo, additional
- Published
- 2021
- Full Text
- View/download PDF
40. Guía de registro para costos de producción de pequeños y medianos agricultores de cultivos transitorios en el piedemonte llanero
- Author
-
Molina Romero, Adriana María, primary, Caicedo Guerrero, Samuel, additional, Ostos Triana, Manuel Eduardo, additional, and Reyes Díaz, Juan Carlos, additional
- Published
- 2020
- Full Text
- View/download PDF
41. A reversible water‐based electrostatic adhesive.
- Author
-
Sierra‐Romero, Adriana, Novakovic, Katarina, and Geoghegan, Mark
- Subjects
- *
PRESSURE-sensitive adhesives , *ADHESIVES , *FOOD labeling , *FOOD packaging , *AUTOMOTIVE electronics , *COVALENT bonds - Abstract
Commercial adhesives typically fall into two categories: structural or pressure sensitive. Structural glues rely on covalent bonds formed during curing and provide high tensile strength whilst pressure‐sensitive adhesives use physical bonding to provide weaker adhesion, but with considerable convenience for the user. Here, a new class of adhesive is presented that is also reversible, with a bond strength intermediate between those of pressure‐sensitive and structural adhesives. Complementary water‐based formulations incorporating oppositely charged polyelectrolytes form electrostatic bonds that may be reversed through immersion in a low or high pH aqueous environment. This electrostatic adhesive has the advantageous property that it exhibits good adhesion to low‐energy surfaces such as polypropylene. Furthermore, it is produced by the emulsion copolymerization of commodity materials, styrene and butyl acrylate, which makes it inexpensive and opens the possibility of industrial production. Bio‐based materials have been also integrated into the formulations to further increase sustainability. Moreover, unlike other water‐based glues, adhesion does not significantly degrade in humid environments. Because such electrostatic adhesives do not require mechanical detachment, they are appropriate for the large‐scale recycling of, e.g., bottle labels or food packaging. The adhesive is also suitable for dismantling components in areas as varied as automotive parts and electronics. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
42. Depletion of backscattered fundamental band signal for nonlinearity parameter imaging
- Author
-
Coila, Andres, primary, Romero, Adriana, additional, Miranda, Edmundo A., additional, Oelze, Michael L., additional, and Lavarello, Roberto, additional
- Published
- 2023
- Full Text
- View/download PDF
43. Unveiling invasive insect threats to plant biodiversity: Leveraging eDNA metabarcoding and saturated salt trap solutions for biosurveillance
- Author
-
Milián-García, Yoamel, primary, Pyne, Cassandre, additional, Lindsay, Kate, additional, Romero, Adriana, additional, and Hanner, Robert H., additional
- Published
- 2023
- Full Text
- View/download PDF
44. Sale of critically endangered sharks in the United States
- Author
-
Ryburn, Savannah J, primary, Yu, Tammy, additional, Ong, Kelly Jia-Wei, additional, Alston, Meggan A, additional, Howie, Ella, additional, LeRoy, Peyton, additional, Giang, Sarah Elizabeth, additional, Ball, William, additional, Benton, Jewel, additional, Calhoun, Robert, additional, Favreau, Isabella, additional, Gutierrez, Ana, additional, Hallac, Kayla, additional, Hanson, Dakota, additional, Hibbard, Teagan, additional, Loflin, Bryson, additional, Lopez, Joshua, additional, Mock, Gracie, additional, Myers, Kailey, additional, Pinos-Sanchez, Andres, additional, Suarez Garcia, Alejandra Maria, additional, Romero, Adriana Retamales, additional, Thomas, Audrey, additional, Williams, Rhiannon, additional, Zaldivar, Anabel, additional, and Bruno, John F, additional
- Published
- 2023
- Full Text
- View/download PDF
45. Squamous Cell Carcinoma
- Author
-
Peña-Romero, Adriana Guadalupe, primary and Dominguez-Cherit, Judith, additional
- Published
- 2020
- Full Text
- View/download PDF
46. Active MR k-space Sampling with Reinforcement Learning
- Author
-
Pineda, Luis, primary, Basu, Sumana, additional, Romero, Adriana, additional, Calandra, Roberto, additional, and Drozdzal, Michal, additional
- Published
- 2020
- Full Text
- View/download PDF
47. Nutrient dynamic in cocoa leaves under different nitrogen sources: a reference tool for foliar analysis/Dinamica nutricional em folhas de cacau sob diferentes fontes de nitrogenio: um instrumento de referencia para a analise foliar
- Author
-
Romero, Melissa Alexandra, Vasquez, Santiago C., Romero, Adriana Elizabeth, Molina-Muller, Marlene Lorena, Capa-Morocho, Mirian Irene, and Granja, Fernando
- Published
- 2022
- Full Text
- View/download PDF
48. Learning normalized inputs for iterative estimation in medical image segmentation
- Author
-
Drozdzal, Michal, Chartrand, Gabriel, Vorontsov, Eugene, Shakeri, Mahsa, Di Jorio, Lisa, Tang, An, Romero, Adriana, Bengio, Yoshua, Pal, Chris, and Kadoury, Samuel
- Published
- 2018
- Full Text
- View/download PDF
49. List of Contributors
- Author
-
Alessandrini, Aurora, primary, Arenas, Roberto, additional, Asz-Sigall, Daniel, additional, de Berker, David, additional, Cervantes, Jessica, additional, Chang, Patricia, additional, Daoud, Alexander, additional, Di Chiacchio, Nilton, additional, Di Chiacchio, Nilton G., additional, Dominguez-Cherit, Judith, additional, Figueira de Mello, Cristina Diniz Borges, additional, Gregoriou, Stamatios, additional, Grover, Chander, additional, Iorizzo, Matilde, additional, Leal-Osuna, Sergio, additional, Lipner, Shari, additional, Noriega, Leandro F., additional, Ormerod, Emma K.C., additional, Pena-Romero, Adriana G., additional, Perper, Marina, additional, Piraccini, Bianca M., additional, Rieder, Evan A., additional, Rigopoulos, Dimitrios, additional, Starace, Michela, additional, Torres-Guerrero, Edoardo, additional, Tosti, Antonella, additional, Vlahovic, Tracey C., additional, and Zaiac, Martin, additional
- Published
- 2019
- Full Text
- View/download PDF
50. Arte público y políticas culturales en el posconflicto: potencias, retos y límites
- Author
-
Roque Romero, Adriana
- Published
- 2018
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.