Abstract Convolutional neural networks (CNNs) have been broadly employed in dermoscopic image analysis, mainly as a result of the large amount of data gathered by the International Skin Imaging Collaboration (ISIC). As in many other medical imaging domains, state‐of‐the‐art methods take advantage of architectures developed for other tasks, frequently assuming full transferability between enormous sets of natural images (e.g. ImageNet) and dermoscopic images, which is not always the case. A comprehensive analysis on the effectiveness of state‐of‐the‐art deep learning techniques when applied to dermoscopic image analysis is provided. To achieve this goal, the authors consider several CNNs architectures and analyse how their performance is affected by the size of the network, image resolution, data augmentation process, amount of available data, and model calibration. Moreover, taking advantage of the analysis performed, a novel ensemble method to further increase the classification accuracy is designed. The proposed solution achieved the third best result in the 2019 official ISIC challenge, with an accuracy of 0.593.

Existing HW/SW platforms for safety-critical systems suffer from limited performance and/or from lack of flexibility due to building on specific proprietary components. This jeopardizes their wide deployment across domains. While some research has been done to overcome these limitations, they have had limited success owing to missing flexibility and extensibility. Flexibility and extensibility are the cornerstones of industry adoption: industries dealing in capital goods need technologies on which they can rely on during decades (e.g. avionics, space, automotive). SELENE aims at covering this gap by proposing a new family of safety-critical computing platforms, which builds upon open source components such as the RISC-V instruction set architecture, GNU/Linux, and the Jailhouse hypervisor. SELENE will develop an advanced computing platform that is able to: (1) adapt the system to the specific requirements of different application domains, to changing environmental conditions, and to internal conditions of the system itself; (2) allow the integration of applications of different criticalities and performance demands in the same platform, guaranteeing functional and temporal isolation properties; (3) achieve flexible diverse redundancy by exploiting the inherent redundant capabilities of the multicore; and (4) efficiently execute compute-intensive applications by means of specific accelerators.

Given the overwhelming impact of machine learning on the last decade, several libraries and frameworks have been developed in recent years to simplify the design and training of neural networks, providing array-based programming, automatic differentiation and user-friendly access to hardware accelerators. None of those tools, however, was designed with native and transparent support for Cloud Computing or heterogeneous High-Performance Computing (HPC). The DeepHealth Toolkit is an open source Deep Learning toolkit aimed at boosting productivity of data scientists operating in the medical field by providing a unified framework for the distributed training of neural networks, which is able to leverage hybrid HPC and cloud environments in a transparent way for the user. The toolkit is composed of a Computer Vision library, a Deep Learning library, and a front-end for non-expert users; all of the components are focused on the medical domain, but they are general purpose and can be applied to any other field. In this paper, the principles driving the design of the DeepHealth libraries are described, along with details about the implementation and the interaction between the different elements composing the toolkit. Finally, experiments on common benchmarks prove the efficiency of each separate component and of the DeepHealth Toolkit overall.

With this work we tackle immunofluorescence classification in renal biopsy, employing state-of-the-art Convolutional Neural Networks. In this setting, the aim of the probabilistic model is to assist an expert practitioner towards identifying the location pattern of antibody deposits within a glomerulus. Since modern neural networks often provide overconfident outputs, we stress the importance of having a reliable prediction, demonstrating that Temperature Scaling (TS), a recently introduced re-calibration technique, can be successfully applied to immunofluorescence classification in renal biopsy. Experimental results demonstrate that the designed model yields good accuracy on the specific task, and that TS is able to provide reliable probabilities, which are highly valuable for such a task given the low inter-rater agreement.

Objectives: A guideline means a protocol designed to help the decision in health system. Whether the protocol is still available for the recent input data is important. The aim of this study is to find a way to monitor the medical guideline, which could help the physician to find out whether the medical guideline is valid for the new patients or a different group of population, and when it should be maintained or updated. Methods: Proportion is the most important variable in diagnostic test. We simulated several pairs of data sets with different proportions. One of each pair was standard and the other had the proportion changed. Two diagnostic tasks had been comparing to find the delay in sample sizes for change detection. Two data management models were used, one of which was acquiring all data before and the other was sliding windows of a fixed size which acquired the most recent samples. Results: The sample sizes for delay detection were calculated with different levels in proportion and changes, and showed with 95% confidence level for estimating. The results also indicate that the sliding window model gave less sample sizes of delay which means more effective. Conclusion: The proper sample sizes could be chosen based on statistical principles in order to estimate the exact change point when it happens, which could help clinicians while monitoring clinical guidelines.

This paper proposes a novel strategy that employs Generative Adversarial Networks (GANs) to augment data in the image segmentation field, and a Convolutional-Deconvolutional Neural Network (CDNN) to automatically generate lesion segmentation mask from dermoscopic images. Training the CDNN with our GAN generated data effectively improves the state-of-the-art.

Social circles detection is a special case of community detection in social network that is currently attracting a growing interest in the research community. In this paper, we propose a two-step technique, making emphasis on the mapping of the data by Restricted Boltzmann Machines (RBMs). Social circles are subsequently inferred by k-means over the preprocessed data. We define different vectorial representations from both structural egonet information and user profile features, and perform a set of tests to adjust the optimal parameters of the RBMs. We study and compare the performance on the ego-Facebook dataset of social circles from Facebook from the Stanford Large Network Dataset Collection. We compare our results with several different baselines.

In the literature, it has been shown that relevance feedback is a good strategy for the system to interact with the user and provide better results in a content-based image retrieval (CBIR) system. On the other hand, there are many retrieval systems which suggest a refinement of the query as the user types, which effectively helps the user to obtain better results with less effort. Based on these observations, in this work we propose to add a suggested query refinement as a complement in an image retrieval system with relevance feedback. Taking advantage of the nature of the relevance feedback, in which the user selects relevant images, the query suggestions are derived using this relevance information. From the results of an evaluation performed, it can be said that this type of query suggestion is a very good enhancement to the relevance feedback scheme, and can potentially lead to better retrieval performance and less effort from the user.

A fundamental problem in image retrieval is how to improve the text-based retrieval systems, which is known as bridging the semantic gap. The reliance on visual similarity for judging semantic similarity may be problematic due to the semantic gap between low-level content and higher-level concepts. One way to overcome this problem and increase thus retrieval performance is to consider user feedback in an interactive scenario. In our approach, a user starts a query and is then presented with a set of (hopefully) relevant images; selecting from these images those which are more relevant to her. Then the system refines its results after each iteration, using late fusion methods, and allowing the user to dynamically tune the amount of textual and visual information that will be used to retrieve similar images. We describe how does our approach fit in a real-world setting, discussing also an evaluation of results.

This paper describes the ICFHR 2010 Contest for quantitative evaluation of binarization algorithms. These algorithm are applied to synthetic images of modern pdf documents with noise from historical documents. Today, many scientists work on the binarization task and many algorithms have been proposed. However, the selection of the most appropriate one is not a simple procedure. The evaluation of these algorithms proved to be another difficult task since there is no objective way to compare the results. Here, 4 groups with 6 systems are participating in the competition. The experimental setting is described in detail. Moreover, a short description of the participating groups, their systems, and the results achieved are finally presented.

It is known that the use of video can help improve the performance of face verification systems. However, processing video in resource constrained devices is prohibitive. In order to reduce the load of the algorithms, a quality-based selection of frames can be applied. Generally there are available several qualities and thus a good fusion scheme is required. This paper addresses the problem of fusing quality measures such that the resulting quality improves the performance of frame selection. A comparison of different methods for fusing qualities is presented. Also, some new quality measures based on time derivatives are proposed, which are shown to be beneficial for estimating the overall quality. Finally, a curve is proposed which proves that the qualities used for frame selection effectively improve verification performance, independent of the number of frames selected or the method employed for obtaining the overall biometric score.

Person recognition using facial features, e.g., mug-shot images, has long been used in identity documents. However, due to the widespread use of web-cams and mobile devices embedded with a camera, it is now possible to realize facial video recognition, rather than resorting to just still images. In fact, facial video recognition offers many advantages over still image recognition; these include the potential of boosting the system accuracy and deterring spoof attacks. This paper presents an evaluation of person identity verification using facial video data, organized in conjunction with the International Conference on Biometrics (ICB 2009). It involves 18 systems submitted by seven academic institutes. These systems provide for a diverse set of assumptions, including feature representation and preprocessing variations, allowing us to assess the effect of adverse conditions, usage of quality information, query selection, and template construction for video-to-video face authentication.

While video tagging (or "concept detection") is a key building block of research prototypes for video retrieval, its practical use is hindered by the computational effort associated with learning and detecting thousands of concepts. Support vector machines (SVMs), which can be considered the standard approach, scale poorly since the number of support vectors is usually high. In this paper, we propose a novel alternative that offers the benefits of rapid training and detection. This linear-discriminative method is based on the maximization of the area under the ROC. In quantitative experiments on a publicly available dataset of Web videos, we demonstrate that this approach offers a significant speedup at a moderate performance loss compared to SVMs, and also outperforms another well-known linear-discriminative method based on a Passive-Aggressive Online Learning (PAMIR).

While hierarchies are powerful tools for organizing content in other application areas, current web video platforms offer only limited support for a taxonomy-based browsing. To overcome this limitation, we present a framework called TubeFiler. Its two key features are an automatic multimodal categorization of videos into a genre hierarchy, and a support of additional fine-grained hierarchy levels based on unsupervised learning. We present experimental results on real-world YouTube clips with a 2-level 46-category genre hierarchy, indicating that - though the problem is clearly challenging - good category suggestions can be achieved. For example, if TubeFiler suggests 5 categories, it hits the right one (or at least its supercategory) in 91.8% of cases.

Computer vision and image recognition research have a great interest in dimensionality reduction techniques. Generally these techniques are independent of the classifier being used and the learning of the classifier is carried out after the dimensionality reduction is performed, possibly discarding valuable information. In this paper we propose an iterative algorithm that simultaneously learns a linear projection base and a reduced set of prototypes optimized for the Nearest-Neighbor classifier. The algorithm is derived by minimizing a suitable estimation of the classification error probability. The proposed approach is assessed through a series of experiments showing a good behavior and a real potential for practical applications.

We present a new method for relevance feedback in image retrieval and a scheme to learn weighted distances which can be used in combination with different relevance feedback methods. User feedback is a crucial step in image retrieval to maximise retrieval performance as was shown in recent image retrieval evaluations. Machine learning is expected to be able to learn how to rank images according to users needs. Most image retrieval systems incorporate user feedback using rather heuristic means and only few groups have formally investigated how to maximise the benefit from it using machine learning techniques. We incorporate our distance-learning method into our new relevance feedback scheme and into two different approaches from the literature. The methods are compared on two publicly available databases, one which is purely content-based and one which uses additional textual information. It is shown that the new relevance feedback scheme outperforms the other methods and that all methods benefit from weighted distance learning.

In order to optimize the accuracy of the Nearest-Neighbor classification rule, a weighted distance is proposed, along with algorithms to automatically learn the corresponding weights. These weights may be specific for each class and feature, for each individual prototype, or for both. The learning algorithms are derived by (approximately) minimizing the Leaving-One-Out classification error of the given training set. The proposed approach is assessed through a series of experiments with UCI/STATLOG corpora, as well as with a more specific task of text classification which entails very sparse data representation and huge dimensionality. In all these experiments, the proposed approach shows a uniformly good behavior, with results comparable to or better than state-of-the-art results published with the same data so far.