Die KI-Suchmaschine für Jobs
Master Thesis Multi-Teacher Distillation of Self-Supervised Models for 3D Perception(m/w/x)
Beschreibung
You will develop a framework for merging pretrained models, focusing on distillation objectives and evaluations to improve model performance in 3D perception tasks.
Lass KI die perfekten Jobs für dich finden!
Lade deinen CV hoch und die Nejo-KI findet passende Stellenangebote für dich.
Anforderungen
- •Master's degree in Computer Science or related field
- •Experience with deep learning frameworks
- •Excellent programming skills in Python
- •Knowledge of perception algorithms is a plus
- •Goal-oriented and structured work style
- •Very good English skills
- •Enrollment at university
Ausbildung
Aufgaben
- •Develop a multi-teacher knowledge distillation framework.
- •Merge multiple pretrained models into a compact backbone.
- •Focus on task-agnostic distillation objectives.
- •Align heterogeneous feature spaces to prevent negative transfer.
- •Integrate supervised teachers trained on unknown tasks.
- •Aim for stronger, general representations with reduced model capacity.
- •Ensure compatibility with existing perception stacks.
- •Conduct structured evaluations using public datasets.
- •Utilize internal real-world data for practical results.
Tools & Technologien
Sprachen
Englisch – verhandlungssicher
- Bosch GroupVollzeitnur vor OrtKeine AngabeRenningen
- Fraunhofer-Gesellschaft
Master Thesis - Out-of-distribution detection + annotation for traversability estimation for robots(m/w/x)
VollzeitPraktikumnur vor OrtStuttgart - Fraunhofer-Gesellschaft
Master Thesis - Multi-modal traversability estimation for Autonomous Outdoor Navigation(m/w/x)
VollzeitPraktikumnur vor OrtStuttgart - Fraunhofer-Gesellschaft
Master Thesis - Multi-session global traversability Mapping for Autonomous Outdoor Navigation(m/w/x)
VollzeitPraktikumnur vor OrtStuttgart - Bosch Group
Master Thesis Deep Learning for Ultrasound(m/w/x)
Vollzeitnur vor OrtKeine AngabeRenningen
Master Thesis Multi-Teacher Distillation of Self-Supervised Models for 3D Perception(m/w/x)
Die KI-Suchmaschine für Jobs
Beschreibung
You will develop a framework for merging pretrained models, focusing on distillation objectives and evaluations to improve model performance in 3D perception tasks.
Lass KI die perfekten Jobs für dich finden!
Lade deinen CV hoch und die Nejo-KI findet passende Stellenangebote für dich.
Anforderungen
- •Master's degree in Computer Science or related field
- •Experience with deep learning frameworks
- •Excellent programming skills in Python
- •Knowledge of perception algorithms is a plus
- •Goal-oriented and structured work style
- •Very good English skills
- •Enrollment at university
Ausbildung
Aufgaben
- •Develop a multi-teacher knowledge distillation framework.
- •Merge multiple pretrained models into a compact backbone.
- •Focus on task-agnostic distillation objectives.
- •Align heterogeneous feature spaces to prevent negative transfer.
- •Integrate supervised teachers trained on unknown tasks.
- •Aim for stronger, general representations with reduced model capacity.
- •Ensure compatibility with existing perception stacks.
- •Conduct structured evaluations using public datasets.
- •Utilize internal real-world data for practical results.
Tools & Technologien
Sprachen
Englisch – verhandlungssicher
Über das Unternehmen
Bosch Group
Branche
IT
Beschreibung
Bosch invents high-quality technologies and services that spark enthusiasm and enrich people’s lives. The company grows together, enjoys work, and inspires each other.
- Bosch Group
Master Thesis Automated Driving Systems(m/w/x)
Vollzeitnur vor OrtKeine AngabeRenningen - Fraunhofer-Gesellschaft
Master Thesis - Out-of-distribution detection + annotation for traversability estimation for robots(m/w/x)
VollzeitPraktikumnur vor OrtStuttgart - Fraunhofer-Gesellschaft
Master Thesis - Multi-modal traversability estimation for Autonomous Outdoor Navigation(m/w/x)
VollzeitPraktikumnur vor OrtStuttgart - Fraunhofer-Gesellschaft
Master Thesis - Multi-session global traversability Mapping for Autonomous Outdoor Navigation(m/w/x)
VollzeitPraktikumnur vor OrtStuttgart - Bosch Group
Master Thesis Deep Learning for Ultrasound(m/w/x)
Vollzeitnur vor OrtKeine AngabeRenningen