Jonathan Weber

Université de Haute-Alsace | UHA · Institut de Recherche en Informatique Mathématiques Automatique et Signal (IRIMAS)

Deep learning models have been shown to be a powerful solution for Time Series Classification (TSC). State-of-the-art architectures, while producing promising results on the UCR and the UEA archives , present a high number of trainable parameters. This can lead to long training with high CO2 emission, power consumption and possible increase in the...

In this paper, we present a new approach of document information extraction by studying the document anatomy where we investigated the possible variants and forms it could have for each document component. To overcome the lack of publicly available document datasets, we used a generated invoice database where we conceived 9 different templates and...

Time series data can be found in almost every domain, ranging from the medical field to manufacturing and wireless communication. Generating realistic and useful exemplars and prototypes is a fundamental data analysis task. In this paper, we investigate a novel approach to generating realistic and useful exemplars and prototypes for time series dat...

Adversarial attacks represent a threat to every deep neural network. They are particularly effective if they can perturb a given model while remaining undetectable. They have been initially introduced for image classifiers, and are well studied for this task. For time series, few attacks have yet been proposed. Most that have are adaptations of att...

Time series averages are one key input to temporal data mining techniques such as classification, clustering, forecasting, etc. In practice, the optimality of estimated averages often impacts the performance of such temporal data mining techniques. Practically, an estimated average is presumed to be optimal if it minimizes the discrepancy between i...

Colorectal cancer is responsible of the death of hundred of thousands of people worldwide each year. The histopathological features of the tumor are generally identified from the analysis of tissue taken from a biopsy providing information for selecting the adequate treatment. With the advent of digital pathology, slides of tissue are increasingl...

The measurement of progress using benchmarks evaluations is ubiquitous in computer science and machine learning. However, common approaches to analyzing and presenting the results of benchmark comparisons of multiple algorithms over multiple datasets, such as the critical difference diagram introduced by Dem\v{s}ar (2006), have important shortcomin...

Land use and land cover and Urban Fabric (UF) mapping are very useful for urban modeling and simulation (growth, pollution, noise, micro-climate, mobility) in a context of global change. In recent years, due to the increase of Earth Observation data researchers built and shared datasets to the machine learning scientific community to apply and test...

Deep Learning models for time series classification are benchmarked on the UCR Archive. This archive contains 128 datasets. Unfortunately only 5 datasets contain more than 1000 training samples. For most deep learning models, this lead to over-fitting. One way to address this issue and improve the generalization of the models is data augmentation....

In the context of global change, up-to-date land use land cover (LULC) maps is a major challenge to assess pressures on natural areas. These maps also allow us to assess the evolution of land cover and to quantify changes over time (such as urban sprawl), which is essential for having a precise understanding of a given territory. Few studies have c...

An Augmented Reality Microscope (ARM) displays additional information about the tissues being analyzed by a pathologist. The image analysis methods used by these microscopes must be robust to changes in magnification level in order to follow the displacements in the glass slides. In this paper, we propose to take advantage of features present in so...

In today’s data-driven world, time series forecasting is one of the intensively investigated temporal data mining technique. In practice, there are a range of forecasting techniques that are proven to be efficient at capturing different aspect of an input. For instance, classic linear forecasting models such as Seasonal Auto-Regressive Integrated M...

This paper presents MultiSenGE that is a new large scale multimodal and multitemporal benchmark dataset covering one of the biggest administrative region located in the Eastern part of France. MultiSenGE contains 8,157 patches of 256 × 256 pixels for the Sentinel-2 L2A , Sentinel-1 GRD images in VV-VH polarization and a Regional large scale Land Us...

Adversarial attacks represent a threat to every deep neural network. They are particularly effective if they can perturb a given model while remaining undetectable. They have been initially introduced for image classifiers, and are well studied for this task. For time series, few attacks have yet been proposed. Most that have are adaptations of att...

Urban areas are increasing since several years as a result of development of built-up areas, network infrastructure, industrial areas or other built-up areas. This urban sprawl has a considerable impact on natural areas by changing the functioning of ecosystems. Mapping and monitoring Urban Fabrics (UF) is therefore relevant for urban planning and...

Time series are ubiquitous in data mining applications. Similar to other types of data, annotations can be challenging to acquire, thus preventing from training time series classification models. In this context, clustering methods can be an appropriate alternative as they create homogeneous groups allowing a better analysis of the data structure....

Nowadays, digital pathology plays a major role in the diagnosis and prognosis of tumours. Unfortunately, existing methods remain limited when faced with the high resolution and size of Whole Slide Images (WSIs) coupled with the lack of richly annotated datasets. Regarding the ability of the Deep Learning (DL) methods to cope with the large scale ap...

Anatomical Pathology dates back to the nineteenth century when Rudolf Virchow introduced his concept of cellular pathology and when the technical improvements of light microscopy enabled wide-spread use of structural criteria to define diseases. Since then, the quality of optical instruments has been constantly evolving. However the central element...

When overpopulated cities face frequent crowded events like strikes, demonstrations, parades or other sorts of people gatherings, they are confronted to multiple security issues. To mitigate these issues, security forces are often involved to monitor the gatherings and to ensure the security of their participants. However, when access to technology...

This paper brings deep learning at the forefront of research into time series classification (TSC). TSC is the area of machine learning tasked with the categorization (or labelling) of time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by...

Staying aware of new approaches emerging within specific areas can be challenging for researchers who have to follow many feeds such as journals articles, authors’ papers, and other basic keyword-based matching algorithms. Hence, this paper proposes an information retrieval process for scientific articles aiming to suggest semantically related arti...

The field of digital pathology emerged with the introduction of whole slide imaging scanners and lead to the development of new tools for analyzing histopathological slides. The availability of digital representation of the slides has motivated the development of artificial intelligence methods to automatically identify microscopic structures in or...

In order to understand web-based application user behavior, web usage mining applies unsupervised learning techniques to discover hidden patterns from web data that captures user browsing on web sites. For this purpose, web session clustering has been among the most popular approaches to group users with similar browsing patterns that reflect their...

Résumé : L’anatomopathologie remonte au 19ème siècle. Depuis, le matériel n’a cessé d’évoluer, mais l’oeil expert du pathologiste reste incontournable. De même, le processus complet (préparation du tissu et des lames, coloration, contrôle qualité) consiste encore en beaucoup d’étapes manuelles. Grâce à l’avènement récent de scanners numériques à bo...

Time series classification (TSC) is the area of machine learning interested in learning how to assign labels to time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE is infeasibl...

Purpose: Manual feedback from senior surgeons observing less experienced trainees is a laborious task that is very expensive, time-consuming and prone to subjectivity. With the number of surgical procedures increasing annually, there is an unprecedented need to provide an accurate, objective and automatic evaluation of trainees' surgical skills in...

Purpose Manual feedback from senior surgeons observing less experienced trainees is a laborious task that is very expensive, time-consuming and prone to subjectivity. With the number of surgical procedures increasing annually, there is an unprecedented need to provide an accurate, objective and automatic evaluation of trainees’ surgical skills in o...

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful app...

Over the past one hundred years, the classic teaching methodology of “see one, do one, teach one” has governed the surgical education systems worldwide. With the advent of Operation Room 2.0, recording video, kinematic and many other types of data during the surgery became an easy task, thus allowing artificial intelligence systems to be deployed a...

Over the past one hundred years, the classic teaching methodology of "see one, do one, teach one" has governed the surgical education systems worldwide. With the advent of Operation Room 2.0, recording video, kinematic and many other types of data during the surgery became an easy task, thus allowing artificial intelligence systems to be deployed a...

Time Series Classification (TSC) problems are encountered in many real life data mining tasks ranging from medicine and security to human activity recognition and food safety. With the recent success of deep neural networks in various domains such as computer vision and natural language processing, researchers started adopting these techniques for...

Deep neural networks have revolutionized many fields such as computer vision and natural language processing. Inspired by this recent success, deep learning started to show promising results for Time Series Classification (TSC). However, neural networks are still behind the state-of-the-art TSC algorithms, that are currently composed of ensembles o...

Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This idea has been shown to improve deep neural network's generalization capabilities in many computer vision tasks...

Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This idea has been shown to improve deep neural network's generalization capabilities in many computer vision tasks...

The need for automatic surgical skills assessment is increasing, especially because manual feedback from senior surgeons observing junior surgeons is prone to subjectivity and time consuming. Thus, automating surgical skills evaluation is a very important step towards improving surgical practice. In this paper, we designed a Convolutional Neural Ne...

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful app...

Data augmentation in deep neural networks is the process of generating artificial data in order to reduce the variance of the classifier with the goal to reduce the number of errors. This idea has been shown to improve deep neural network's generalization capabilities in many computer vision tasks such as image recognition and object localization....

Objective: The analysis of surgical motion has received a growing interest with the development of devices allowing their automatic capture. In this context, the use of advanced surgical training systems makes an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in...

The need for automatic surgical skills assessment is increasing, especially because manual feedback from senior surgeons observing junior surgeons is prone to subjectivity and time consuming. Thus, automating surgical skills evaluation is a very important step towards improving surgical practice. In this paper, we designed a Convolutional Neural Ne...

Because of the data deluge in scientific publication, finding relevant information is getting harder and harder for researchers and readers. Building an enhanced scientific search engine by taking semantic relations into account poses a great challenge. As a starting point, semantic relations between keywords from scientific articles could be extra...

This paper focuses on producing accurate segmentation of a set of images at different scales. In the process of image co-segmentation, we turn our attention to the task of computing dense correspondences between a set of images. These correspondences are calculated in a dense grid of pixels, where each pixel is represented by an invariant descripto...

In this paper, we propose a comparative study of various segmentation methods applied to the extraction of tree leaves from natural images. This study follows the design of a mobile application, developed by Cerutti et al. (published in ReVeS Participation - Tree Species Classification Using Random Forests and Botanical Features. CLEF 2012), to hig...

emplate matching is a fundamental problem in image analysis and computer vision. It has been addressed very early by Mathematical Morphology, through the well-known Hit-or-Miss Transform. In this chapter, we review most of the existing works on this morphological template matching operator, from the standard case of binary images to the (not so sta...

Earth observation satellites are now providing images with short revisit cycle and high spatial resolution. The amount of produced data requires new methods that will give a sound temporal analysis while being computationally efficient. Dynamic time warping has proved to be a very sound measure to capture similarities in radiometric evolutions. In...

Quasi-flat zones enable the computation of homogeneous image regions with respect to one or more arbitrary criteria, such as pixel intensity. They are most often employed in simplification and segmentation, while multiple strategies exist for their application to color data as well. In this paper we explore a vector ordering based alternative metho...

Quasi-flat zones are morphological operators which segment the image into homogeneous regions according to certain criteria. They are used as an image simplification tool or an image segmentation pre-processing, but they induced a very important oversegmentation. Several filtering methods have been proposed to deal with this issue but they suffer f...

Template matching is a very topical issue in a wide range of imaging applications. Mathematical morphology offers the hit-or-miss transform, an operator which has been successfully applied for template matching in binary images. More recently, it has been extended to grayscale images and even to multivariate images. Nevertheless, these extensions,...

Symbol retrieval for technical documents is still a hot challenge in the document analysis community. In this paper we propose another way to spot symbols. A pixel-based template operator which is an adaptation of the hit-or-miss transform is defined. This operator is robust to translation, rotation and reflection. Experimental results on a real ap...

This paper proposes to revisit a recent interactive segmentation algorithm based on an original image representation called the component-tree [1]. This method relies on an optimisation process allowing to choose a segmentation result fitting at best some image markers defined by the user. We propose different solutions to improve the efficiency of...

Satellite Image Time Series (SITS, for short) are useful resources for Earth monitoring. Upcoming satellites will provide a global coverage of the Earth's surface with a short revisit time (five days); a huge amount of data to analyze will be produced. In order to be able to analyze efficiently and accurately these images, new methods have to be de...