Ivan Reyes-Amezcua

Center for Research and Advanced Studies of the National Polytechnic Institute

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Gilberto Ochoa‐Ruiz

Tecnológico de Monterrey

Andres Méndez-Vázquez

Center for Research and Advanced Studies of the National Polytechnic Institute

Daniel Flores-Araiza

Tecnológico de Monterrey

Christian Daul

Université de Lorraine

Francisco Lopez-Tiro

Tecnológico de Monterrey

Jorge Gonzalez-Zapata

Center for Research and Advanced Studies of the National Polytechnic Institute

Mauricio Méndez-Ruiz

Tecnológico de Monterrey

Jacques Hubert

Centre Hospitalier Régional et Universitaire de Nancy

Juan Pablo Betancur-Rengifo

Tecnológico de Monterrey

Ricardo Espinosa

Universidad Panamericana

Cooperative Institutions

Tecnológico de Monterrey

Center for Research and Advanced Studies of the National Polytechnic Institute

Université de Lorraine

Instituto Politécnico Nacional

Centre Hospitalier Régional et Universitaire de Nancy

Inserm

Centre National de la Recherche Scientifique

ORCID

Centre de Recherche en Automatique de Nancy

Universidad Panamericana

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

LatinX in AI at Computer Vision and Pattern Recognition Conference 2022

Jorge Gonzalez-Zapata Ivan Reyes-Amezcua Daniel Flores-Araiza Mauricio Méndez-Ruiz Gilberto Ochoa‐Ruiz

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning.However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to the difficulty of the dataset caused by a distributional shift in the data.These represent a significant drawback when attempting to learn the underlying data manifold.Therefore, there is a pressing need to develop better ways of obtaining generalization and representation of the underlying manifold.In this paper, we propose a novel approach to DML that we call Guided Deep Metric Learning, a novel architecture oriented to learning more compact clusters, improving generalization under distributional shifts in DML.This novel architecture consists of two independent models: A multi-branch master model, inspired from a Few-Shot Learning (FSL) perspective, generates a reduced hypothesis space based on prior knowledge from labeled data, which guides or regularizes the decision boundary of a student model during training under an offline knowledge distillation scheme.Experiments have shown that the proposed method is capable of a better manifold generalization and representation to up to 40% improvement (Recall@1, CIFAR10), using guidelines suggested by Musgrave et al. to perform a more fair and realistic comparison, which is currently absent in the literature.

10.52591/lxai202206241

Cite

Citations (0)

EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction

Lecture notes in computer science (2024)

Ivan Reyes-Amezcua Ricardo Espinosa Christian Daul Gilberto Ochoa‐Ruiz Andres Méndez-Vázquez

Robustness

Benchmark (surveying)

Strengths and weaknesses

Monocular

10.1007/978-3-031-73748-0_9

Cite

Citations (0)

Improving Automatic Endoscopic Stone Recognition Using a Multi-view Fusion Approach Enhanced with Two-Step Transfer Learning

Francisco Lopez-Tiro Elias Villalvazo-Avila Juan Pablo Betancur-Rengifo Ivan Reyes-Amezcua Jacques Hubert

This contribution presents a deep-learning method for extracting and fusing image information acquired from different viewpoints, with the aim to produce more discriminant object features for the identification of the type of kidney stones seen in endoscopic images. The approach was specifically designed to mimic the morpho-constitutional analysis to visually classify kidney stones by jointly using surface and section images of kidney stone fragments. The model was further improved with a two-step transfer learning approach and by attention blocks to refine the learned feature maps. Deep feature fusion strategies improved the results of single view extraction backbone models by more than 6% in terms of accuracy of the kidney stones classification.

Viewpoints

Feature (linguistics)

Transfer of learning

Identification

10.1109/iccvw60793.2023.00450

Cite

Citations (2)

MACFE: A Meta-learning and Causality Based Feature Engineering Framework

arXiv (Cornell University) (2022)

Ivan Reyes-Amezcua Daniel Flores-Araiza Gilberto Ochoa‐Ruiz Andres Méndez-Vázquez Eduardo Rodríguez-Tello

Feature engineering has become one of the most important steps to improve model prediction performance, and to produce quality datasets. However, this process requires non-trivial domain-knowledge which involves a time-consuming process. Thereby, automating such process has become an active area of research and of interest in industrial applications. In this paper, a novel method, called Meta-learning and Causality Based Feature Engineering (MACFE), is proposed; our method is based on the use of meta-learning, feature distribution encoding, and causality feature selection. In MACFE, meta-learning is used to find the best transformations, then the search is accelerated by pre-selecting "original" features given their causal relevance. Experimental evaluations on popular classification datasets show that MACFE can improve the prediction performance across eight classifiers, outperforms the current state-of-the-art methods in average by at least 6.54%, and obtains an improvement of 2.71% over the best previous works.

Feature Engineering

Feature (linguistics)

Relevance

Causality

10.48550/arxiv.2207.04010

Cite

Citations (0)

Enforcing Class Separability in Metric Learning Via Two Novel Distance-Based Loss Functions for Few-Shot Image Classification

Gilberto Ochoa‐Ruiz Mauricio Méndez-Ruiz Jorge Gonzalez-Zapata Ivan Reyes-Amezcua Daniel Flores-Araiza

Few-shot learning is a challenging area of research that aims to learn new concepts with only a few labeled samples of data. Recent works based on metric-learning approaches leverage the meta-learning approach, which is encompassed by episodic tasks that make use a support (training) and query set (test) with the objective of learning a similarity comparison metric between those sets. Due to the lack of data, the learning process of the embedding network becomes an important part of the few-shot task. Previous works have addressed this problem using metric learning approaches, but the properties of the underlying latent space and the separability of the difference classes on it was not entirely enforced. In this work, we propose two different loss functions which consider the importance of the embedding vectors by looking at the intra-class and inter-class distance between the few data. The first loss function is the Proto-Triplet Loss, which is based on the original triplet loss with the modifications needed to better work on few-shot scenarios. The second loss function, which we dub ICNN loss is based on an inter and intra class nearest neighbors score, which help us to assess the quality of embeddings obtained from the trained network. Our results, obtained from a extensive experimental setup show a significant improvement in accuracy in the miniImagenNet benchmark compared to other metric-based few-shot learning methods by a margin of 2%, demonstrating the capability of these loss functions to allow the network to generalize better to previously unseen classes. In our experiments, we demonstrate competitive generalization capabilities to other domains, such as the Caltech CUB, Dogs and Cars datasets compared with the state of the art.

One shot

10.2139/ssrn.4488078

Cite

Citations (0)

LatinX in AI at Computer Vision and Pattern Recognition Conference 2022

Jorge Gonzalez-Zapata Ivan Reyes-Amezcua Daniel Flores-Araiza Mauricio Méndez-Ruiz Gilberto Ochoa‐Ruiz

10.52591/lxai202206240

Cite

Citations (0)

Evaluating the plausibility of synthetic images for improving automated endoscopic stone recognition

Ruben Gonzalez-Perez Francisco Lopez-Tiro Ivan Reyes-Amezcua Eduardo Falcon-Morales Rosa-Maria Rodríguez-Guéant

Currently, the Morpho-Constitutional Analysis (MCA) is the de facto approach for the etiological diagnosis of kidney stone formation, and it is an important step for establishing personalized treatment to avoid relapses. More recently, research has focused on performing such tasks intra-operatively, an approach known as Endoscopic Stone Recognition (ESR). Both methods rely on features observed in the surface and the section of kidney stones to separate the analyzed samples into several sub-groups. However, given the high intra-observer variability and the complex operating conditions found in ESR, there is a lot of interest in using AI for computer-aided diagnosis. However, current AI models require large datasets to attain a good performance and for generalizing to unseen distributions. This is a major problem as large labeled datasets are very difficult to acquire, and some classes of kidney stones are very rare. Thus, in this paper, we present a method based on diffusion as a way of augmenting pre-existing ex-vivo kidney stone datasets. Our aim is to create plausible diverse kidney stone images that can be used for pre-training models using ex-vivo data. We show that by mixing natural and synthetic images of CCD images, it is possible to train models capable of performing very well on unseen intra-operative data. Our results show that is possible to attain an improvement of 10% in terms of accuracy compared to a baseline model pre-trained only on ImageNet. Moreover, our results show an improvement of 6% for surface images and 10% for section images compared to a model train on CCD images only, which demonstrates the effectiveness of using synthetic images.

Ground truth

Synthetic data

10.1109/cbms61543.2024.00029

Cite

Citations (0)

Annual Forecast of Photovoltaic Power Generation Based on MLP Artificial Neural Networks

ECORFAN Journal-Democratic Republic of Congo (2023)

Martin Garcia-Hernandez Ivan Reyes-Amezcua Jeronimo Rodriguez-Armenta Ekhine Garcia‐Garcia

The intermittency of solar energy resources presents a significant challenge in balancing power generation and load demand. To enhance system consistency, forecasting photovoltaic solar energy is crucial. Among numerous techniques, Artificial Neural Network (ANN) is an efficient tool that can help simplify this problem and predict photovoltaic power generation based on various inputs such as weather data and panel characteristics. In this paper, we present the results of an annual forecast of photovoltaic power generation based on Multilayer Perceptrons (MLP), which provides valuable insights into the potential of MLP ANN for accurate and reliable prediction of photovoltaic power generation, thereby improving the efficiency and reliability of photovoltaic systems. The results were obtained based on data collected over a year and validated with data from the following year. Mean Squared Error (MSE) was utilized to quantify the error between the predicted and measured photovoltaic solar energy generation. The analysis demonstrated that this annual forecast of photovoltaic power generation is highly accurate.

10.35429/ejdrc.2023.17.9.1.5

Cite

Citations (0)

Guided Deep Metric Learning

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2022)

Jorge Gonzalez-Zapata Ivan Reyes-Amezcua Daniel Flores-Araiza Mauricio Méndez-Ruiz Gilberto Ochoa‐Ruiz

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to the difficulty of the dataset caused by a distributional shift in the data. These represent a significant drawback when attempting to learn the underlying data manifold. Therefore, there is a pressing need to develop better ways of obtaining generalization and representation of the underlying manifold. In this paper, we propose a novel approach to DML that we call Guided Deep Metric Learning, a novel architecture oriented to learning more compact clusters, improving generalization under distributional shifts in DML. This novel architecture consists of two independent models: A multi-branch master model, inspired from a Few-Shot Learning (FSL) perspective, generates a reduced hypothesis space based on prior knowledge from labeled data, which guides or regularizes the decision boundary of a student model during training under an offline knowledge distillation scheme. Experiments have shown that the proposed method is capable of a better manifold generalization and representation to up to 40% improvement (Recall@1, CIFAR10), using guidelines suggested by Musgrave et al. to perform a more fair and realistic comparison, which is currently absent in the literature.

Representation

Similarity (geometry)

Feature Learning

Manifold (fluid mechanics)

10.1109/cvprw56347.2022.00154

Cite

Citations (6)

Enhancing Image Classification Robustness through Adversarial Sampling with Delta Data Augmentation (DDA)

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2024)

Ivan Reyes-Amezcua Gilberto Ochoa‐Ruiz Andres Méndez-Vázquez

Robustness

10.1109/cvprw63382.2024.00032

Cite

Citations (1)