Emplois actuels liés à Analysis and integration of class imbalance in deep learning architectures for melanoma detection - Villeurbanne, Auvergne-Rhône-Alpes - CESI Villeurbanne

  • Enhancing tool detection through data augmentation and transfer learning Strategies in Industry 5.0

    il y a 4 jours

    Villeurbanne, Auvergne-Rhône-Alpes, France CESI Villeurbanne Temps plein

    [STAGE MASTER 2 ] - Enhancing tool detection through data augmentation and transfer learning Strategies in Industry 5.0Réf ABG-134860Stage master 2 / IngénieurDurée 6 moisSalaire net mensuel euros22/12/2025CESI VILLEURBANNELieu de travailVILLEURBANNE Auvergne-Rhône-Alpes FranceChamps scientifiquesNumériqueInformatiqueMots clésAffordance; Computer...

  • Additive Manufacturing Engineer

    il y a 4 jours

    Villeurbanne, Auvergne-Rhône-Alpes, France GE Vernova Temps plein

    Job Description SummaryEs-tu un(e) ingénieur(e) en Intelligence Artificielle et Apprentissage Automatique (IA/ML) expérimenté(e), passionné(e) et orienté(e) vers les résultats, prêt(e) à stimuler l'innovation dans le domaine crucial de la transmission d'énergie ?Nous recherchons une personne talentueuse pour concevoir, développer et déployer des...

  • Internship M2 in Industrial Engineering H/F

    il y a 4 heures

    Villeurbanne, Auvergne-Rhône-Alpes, France CESI Temps plein

    Title:  Two-level dynamic scheduling for a reconfigurable production systemKeywords : RMS, Scheduling, Bi-level optimization, Discrete-event SimulationDescriptionIn an industrial context characterized by growing demand uncertainty, high product variability, and significant cost and deadline constraints, Reconfigurable Manufacturing Systems (RMS) offer a...

  • RAM Group Manager

    il y a 2 semaines

    Villeurbanne, Auvergne-Rhône-Alpes, France Alstom Temps plein

    Req ID:502941At Alstom, we understand transport networks and what moves people. From high-speed trains, metros, monorails, and trams, to turnkey systems, services, infrastructure, signalling and digital mobility, we offer our diverse customers the broadest portfolio in the industry. Every day, 80,000 colleagues lead the way to greener and smarter mobility...

  • RAM Group Manager

    il y a 2 semaines

    Villeurbanne, Auvergne-Rhône-Alpes, France ALSTOM Temps plein

    Req ID:502941At Alstom, we understand transport networks and what moves people. From high-speed trains, metros, monorails, and trams, to turnkey systems, services, infrastructure, signalling and digital mobility, we offer our diverse customers the broadest portfolio in the industry. Every day, 80,000 colleagues lead the way to greener and smarter mobility...

  • Confinement effects in surfactant-driven Marangoni flows

    il y a 4 jours

    Villeurbanne, Auvergne-Rhône-Alpes, France Université Claude Bernard Lyon 1 Temps plein

    Confinement effects in surfactant-driven Marangoni flowsRéf ABG-134788Sujet de Thèse15/12/2025Autre financement publicUniversité Claude Bernard Lyon 1Lieu de travailVilleurbanne - Auvergne-Rhône-Alpes - FranceIntitulé du sujetConfinement effects in surfactant-driven Marangoni flowsChamps scientifiquesSciences de l'ingénieurMathématiquesPhysiqueMots...

  • Ingénieur(e) Système Protection

    il y a 4 jours

    Villeurbanne, Auvergne-Rhône-Alpes, France GE Vernova Temps plein

    Job Description SummaryEn tant qu'Ingénieur(e) Système de Protection, vous reporterez au Responsable Ingénierie Contrôle et Protection et vous ferez partie d'une équipe d'ingénieur(e)s hautement motivé(e)s et dynamiques travaillant sur les exigences, la conception, l'intégration, l'installation et la mise en service du système de contrôle et de...

  • Senior Bid Manager

    il y a 4 heures

    Villeurbanne, Auvergne-Rhône-Alpes, France GE Vernova Temps plein

    Job Description SummaryBecome part of a winning team and help to deliver the Green Energy transition.Within Grid Solutions, the Grid Systems Integration (GSI) Business Line, is accountable for the Product Development, for the Business Development, for the Sales, for the Project Execution and for the Services of high voltage Alternative, FACTS & Direct...

  • Project Cybersecurity Lead

    il y a 4 jours

    Villeurbanne, Auvergne-Rhône-Alpes, France GE Vernova Temps plein

    Job Description SummaryCompte tenu des exigences accrues en matière de cybersécurité des technologies opérationnelles (OT), l'Ingénieur(e) en cybersécurité doit travailler sur les spécifications et fournir le support nécessaire conformément à la stratégie de l'entreprise ainsi qu'aux exigences des clients.Grid Solutions, une entreprise du groupe...

  • Stage éco-conception et Analyse du Cycle de Vie

    il y a 4 jours

    Villeurbanne, Auvergne-Rhône-Alpes, France GE Vernova Temps plein

    Job Description SummaryEn tant que nouveau leader mondial indépendant dans le secteur de l'énergie électrique, la mission et l'objectif de GE Vernova d'électrifier et de décarboniser le monde n'ont jamais été aussi clairs et prioritaires. La division PT, Power Transmission de GE VERNOVA Grid Solutions fabrique des équipements pour le réseau...

Analysis and integration of class imbalance in deep learning architectures for melanoma detection

il y a 4 heures

Villeurbanne, Auvergne-Rhône-Alpes, France CESI Villeurbanne Temps plein
[STAGE MASTER 2 ] - Analysis and integration of class imbalance in deep learning architectures for melanoma detection

Réf ABG-135317

Stage master 2 / Ingénieur

Durée 6 mois

Salaire net mensuel euros

28/01/2026

CESI VILLEURBANNE

Lieu de travail

VILLEURBANNE Auvergne-Rhône-Alpes France

Champs scientifiques

  • Numérique
  • Informatique

Mots clés

Class Imbalance, Long-Tailed Learning, Deep Learning, Melanoma, Medical Imaging

Établissement recruteur
Site web :
Lab presentation

CESI LINEACT (UR 7527), Laboratory for Digital Innovation for Businesses and Learning to Support the Competitiveness of Territories, anticipates and accompanies the technological mutations of sectors and services related to industry and construction. The historical proximity of CESI with companies is a determining element for our research activities. It has led us to focus our efforts on applied research close to companies and in partnership with them. A human-centered approach coupled with the use of technologies, as well as territorial networking and links with training, have enabled the construction of cross-cutting research; it puts humans, their needs and their uses, at the center of its issues and addresses the technological angle through these contributions.

Its research is organized according to two interdisciplinary scientific teams and several application areas.

  • Team 1 "Learning and Innovating" mainly concerns Cognitive Sciences, Social Sciences and Management Sciences, Training Techniques and those of Innovation. The main scientific objectives are the understanding of the effects of the environment, and more particularly of situations instrumented by technical objects (platforms, prototyping workshops, immersive systems...) on learning, creativity and innovation processes.
  • Team 2 "Engineering and Digital Tools" mainly concerns Digital Sciences and Engineering. The main scientific objectives focus on modeling, simulation, optimization and data analysis of cyber physical systems. Research work also focuses on decision support tools and on the study of human-system interactions in particular through digital twins coupled with virtual or augmented environments.

Research intersects across the application domains of the Factory of the Future and the City of the Future.

Description

Keywords: Class Imbalance, Long-Tailed Learning, Deep Learning, Melanoma, Medical Imaging.

Internship Topic

Melanoma is an aggressive and potentially fatal skin cancer, representing a major public health issue with an increasing incidence in France. Computer-Aided Diagnosis (CAD) systems, particularly those based on deep neural networks applied to dermoscopic images, have shown promising performance for early melanoma detection.

However, datasets used in this context are often highly imbalanced, as some lesion categories are much rarer than others. This imbalance introduces significant bias in model training and degrades performance on minority classes. Numerous approaches have been proposed in the literature to address this issue, including resampling strategies, loss re-weighting, and decoupled learning [1, 2]. In this internship, the objective is to further investigate loss-function-based approaches, particularly margin-based loss functions [3, 4]. For instance, modifications of the cross-entropy loss will be explored to enforce larger margins between rare and dominant classes, inspired by recent advances in long-tailed visual recognition [5].

Internship Objective

To study, develop, and integrate class-imbalance-aware loss functions into deep learning architectures for dermoscopic image classification.

Methodology

  • State-of-the-art review on class imbalance and long-tailed learning.
  • Implementation of advanced loss functions (margin-based loss, re-weighting).
  • Training and evaluation of deep neural networks on imbalanced datasets.
  • Comparative performance analysis on minority and majority classes.

Expected Outcomes

  • Improved robustness of models to class imbalance.
  • Enhanced classification performance on minority classes.
  • Potential scientific publication.
Bibliography

[1] Lu YANG et al. « A Survey on Long-Tailed Visual Recognition ». en. In : Int J Comput Vis juill. 2022), p ISSN : DOI : / s

[2] Yifan ZHANG et al. Deep Long-Tailed Learning : A Survey. arXiv : [cs]. Oct DOI : /arXiv

[3] Foahom Gouabou, A. C., Iguernaissi, R., Damoiseaux, J. L., Moudafi, A., & Merad, D End-to-End Decoupled Training: A Robust Deep Learning Method for Long-Tailed Classification of Dermoscopic Images for Skin Lesion Classification. Electronics, 11(20), 3275

[4] Foahom Gouabou, A. C., Iguernaissi, R., Damoiseaux, J. L., Moudafi, A., & Merad, D End-to-End Decoupled Training: A Robust Deep Learning Method for Long-Tailed Classification of Dermoscopic Images for Skin Lesion Classification. Electronics, 11(20), 3275

[5] Youngkyu HONG et al. « Disentangling label distribution for long-tailed visual recognition ». In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021, p DOI : /arXiv

Profil

Required Profile

  • Student in the final year of a Master's program or engineering school, specializing in computer science, computer vision, artificial intelligence, industrial engineering, or a related field.

  • Experience with the Unity environment is a plus.

  • Ability to work autonomously and rigorously, while also collaborating effectively within a multidisciplinary research team.

  • Good written and oral communication skills, especially for scientific writing and presenting research results.

Prise de fonction

Dès que possible