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.

Abstract
Ordinal classification is a specific and demanding task, where the aim is not only to increase accuracy, but to also capture the natural order between the classes, and penalize incorrect predictions by how much they deviate from this ranking. If an ordinal classifier must be able to comply with all these requirements, a suitable ordinal metric must be able to accurately measure its degree of compliance. However, the current metrics are unable to completely capture these considerations when assessing classification performance. Moreover, most suffer from sensitivity to imbalanced classes, very common in ordinal classification. In this paper, we propose two variants of a novel performance index that accounts for both accuracy and ranking in the performance assessment of ordinal classification, and is robust against imbalanced classes. © 2018 IEEE.

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.

Abstract
Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.

Abstract
Interpretability is a fundamental property for the acceptance of machine learning models in highly regulated areas. Recently, deep neural networks gained the attention of the scientific community due to their high accuracy in vast classification problems. However, they are still seen as black-box models where it is hard to understand the reasons for the labels that they generate. This paper proposes a deep model with monotonic constraints that generates complementary explanations for its decisions both in terms of style and depth. Furthermore, an objective framework for the evaluation of the explanations is presented. Our method is tested on two biomedical datasets and demonstrates an improvement in relation to traditional models in terms of quality of the explanations generated. © Springer Nature Switzerland AG 2018.

Abstract
Two limitations hamper performance of deep architectures for classification and/or detection in medical imaging: (i) the small amount of available data, and (ii) the class imbalance scenario. While millions of labeled images are available today to build classification tools for natural scenes, the amount of available annotated data for automatic breast cancer screening is limited to a few thousand images, at best. We address these limitations with a method for data augmentation, based on the introduction of random elastic deformations on images of mammograms. We validate this method on three publicly available datasets. Our proposed Convolutional Neural Network (CNN) archi-tecture is trained for mass classification - in a conventional way - , and then used in the more interesting problem of mass detection in full mammograms by transforming the CNN into a Fully Convolutional Network (FCN). © 2018 IEEE.