Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por Ricardo Pereira Cruz

2018

Binary ranking for ordinal class imbalance

Autores
Cruz, R; Fernandes, K; Costa, JFP; Ortiz, MP; Cardoso, JS;

Publicação
PATTERN ANALYSIS AND APPLICATIONS

Abstract
Imbalanced classification has been extensively researched in the last years due to its prevalence in real-world datasets, ranging from very different topics such as health care or fraud detection. This literature has long been dominated by variations of the same family of solutions (e.g. mainly resampling and cost-sensitive learning). Recently, a new and promising way of tackling this problem has been introduced: learning with scoring pairwise ranking so that each pair of classes contribute in tandem to the decision boundary. In this sense, the paper addresses the problem of class imbalance in the context of ordinal regression, proposing two novel contributions: (a) approaching the imbalance by binary pairwise ranking using a well-known label decomposition ensemble, and (b) introducing a regularization into this ensemble so that parallel decision boundaries are favored. These are two independent contributions that synergize well. Our model is tested using linear Support Vector Machines and our results are compared against state-of-the-art models. Both approaches show promising performance in ordinal class imbalance, with an overall 15% improvement relative to the state-of-the-art, as evaluated by a balanced metric.

2018

Deep Image Segmentation by Quality Inference

Autores
Fernandes, K; Cruz, R; Cardoso, JS;

Publicação
2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

Abstract
Traditionally, convolutional neural networks are trained for semantic segmentation by having an image given as input and the segmented mask as output. In this work, we propose a neural network trained by being given an image and mask pair, with the output being the quality of that pairing. The segmentation is then created afterwards through backpropagation on the mask. This allows enriching training with semi-supervised synthetic variations on the ground-truth. The proposed iterative segmentation technique allows improving an existing segmentation or creating one from scratch. We compare the performance of the proposed methodology with state-of-the-art deep architectures for image segmentation and achieve competitive results, being able to improve their segmentations. © 2018 IEEE.

2019

Automatic Augmentation by Hill Climbing

Autores
Cruz, R; Costa, JFP; Cardoso, JS;

Publicação
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: DEEP LEARNING, PT II

Abstract
When learning from images, it is desirable to augment the dataset with plausible transformations of its images. Unfortunately, it is not always intuitive for the user how much shear or translation to apply. For this reason, training multiple models through hyperparameter search is required to find the best augmentation policies. But these methods are computationally expensive. Furthermore, since they generate static policies, they do not take advantage of smoothly introducing more aggressive augmentation transformations. In this work, we propose repeating each epoch twice with a small difference in data augmentation intensity, walking towards the best policy. This process doubles the number of epochs, but avoids having to train multiple models. The method is compared against random and Bayesian search for classification and segmentation tasks. The proposal improved twice over random search and was on par with Bayesian search for 4% of the training epochs.

2019

Insulator visual non-conformity detection in overhead power distribution lines using deep learning

Autores
Prates, RM; Cruz, R; Marotta, AP; Ramos, RP; Simas Filho, EF; Cardoso, JS;

Publicação
COMPUTERS & ELECTRICAL ENGINEERING

Abstract
Overhead Power Distribution Lines (OPDLs) correspond to a large percentage of the medium-voltage electrical systems. In these networks, visual inspection activities are usually performed without resorting to automated systems, requiring a significant investment of time and human resources. We present a methodology to identify the defect and type of insulators using Convolutional Neural Networks (CNNs). More than 2500 photographs were collected both from inside a studio and from a realistic OPDL. A classification model is proposed to automatically recognize the insulators conformity. This model is able to learn from indoors photographs by augmenting these images with realistic details such as top ties and real-world backgrounds. Furthermore, Multi-Task Learning (MTL) was used to improve performance of defect detection by also predicting the insulator class. The proposed methodology is able to achieve an accuracy of 92% for material classification and 85% for defect detection, with F1-score of 0.75, surpassing available solutions.

2019

Averse Deep Semantic Segmentation

Autores
Cruz, R; Costa, JFP; Cardoso, JS;

Publicação
2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)

Abstract
Semantic segmentation consists in predicting whether any given pixel is part of the object of interest or not. Two types of errors are therefore possible: false positives and false negatives. For visualization and emphasis purposes, we might want to put special effort into reducing one type of error in detriment of the other. A common practice is to define the two types of errors as a relative trade-off using a cost matrix. However, it might be more natural for humans to define the trade-off in terms of an absolute constraint on one type of errors while trying to minimize the other. Previously, we suggested possible approaches to introduce this absolute trade-off in binary classifiers. Extending to semantic segmentation, we propose a threshold on the sigmoid layer and modifications to gradient descent such as adding a new term to the loss function and training in two phases. The latter produced the more resilient results, with a simple threshold being sufficient in most cases.

2020

Correction to: Interpretable and Annotation-Efficient Learning for Medical Image Computing

Autores
Cardoso, JS; Nguyen, HV; Heller, N; Abreu, PH; Isgum, I; Silva, W; Cruz, R; Amorim, JP; Patel, V; Roysam, B; Zhou, SK; Jiang, SB; Le, N; Luu, K; Sznitman, R; Cheplygina, V; Mateus, D; Trucco, E; Sureshjani, SA;

Publicação
Interpretable and Annotation-Efficient Learning for Medical Image Computing - Third International Workshop, iMIMIC 2020, Second International Workshop, MIL3ID 2020, and 5th International Workshop, LABELS 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4-8, 2020, Proceedings

Abstract

  • 2
  • 5