Master Thesis Multi-Teacher Distillation of Self-Supervised Models for 3D Perception

Böblingen - Germany

Monthly Salary: Not Disclosed

Posted on: 3 hours ago

Vacancies: 1 Vacancy

Job Summary

Self-supervised learning (SSL) and foundation models have advanced 3D perception for LiDAR and radar but current models are trained independently leading to fragmented representations.

During your thesis you will develop a multi-teacher knowledge distillation framework to merge multiple pretrained models into a single compact backbone without labeled data.
You will focus on task-agnostic distillation objectives to align heterogeneous feature spaces and prevent negative transfer with extensions to integrate supervised teachers trained on unknown tasks. The resulting model will aim to deliver stronger more general representations reduced model capacity and compatibility with existing perception stacks.
Furthermore you will conduct structured evaluations using both public datasets and internal real-world data striving for excellent theoretical and practical results.

Qualifications :

Education: Master studies in the field of Computer Science Robotics Engineering Natural Sciences or comparable with excellent academic achievements
Experience and Knowledge: experience with deep learning and corresponding frameworks; excellent programming skills (Python); knowledge of perception algorithms is a plus
Personality and Working Practice: you excel at goal-oriented and structured work are highly self-motivated flexible and apply logical thinking to maintain project oversight
Languages: very good in English

Additional Information :

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV transcript of records examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore we welcome all applications regardless of gender age disability religion ethnic origin or sexual identity.

Need further information about the job
Mohamed Abdelsamad (Functional Department)

#LI-DNI

Remote Work :

Employment Type :

Full-time

Self-supervised learning (SSL) and foundation models have advanced 3D perception for LiDAR and radar but current models are trained independently leading to fragmented representations.During your thesis you will develop a multi-teacher knowledge distillation framework to merge multiple pretrained mo...

Self-supervised learning (SSL) and foundation models have advanced 3D perception for LiDAR and radar but current models are trained independently leading to fragmented representations.

During your thesis you will develop a multi-teacher knowledge distillation framework to merge multiple pretrained models into a single compact backbone without labeled data.
You will focus on task-agnostic distillation objectives to align heterogeneous feature spaces and prevent negative transfer with extensions to integrate supervised teachers trained on unknown tasks. The resulting model will aim to deliver stronger more general representations reduced model capacity and compatibility with existing perception stacks.
Furthermore you will conduct structured evaluations using both public datasets and internal real-world data striving for excellent theoretical and practical results.

Qualifications :

Education: Master studies in the field of Computer Science Robotics Engineering Natural Sciences or comparable with excellent academic achievements
Experience and Knowledge: experience with deep learning and corresponding frameworks; excellent programming skills (Python); knowledge of perception algorithms is a plus
Personality and Working Practice: you excel at goal-oriented and structured work are highly self-motivated flexible and apply logical thinking to maintain project oversight
Languages: very good in English

Additional Information :

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV transcript of records examination regulations and if indicated a valid work and residence permit.

Need further information about the job
Mohamed Abdelsamad (Functional Department)

#LI-DNI

Remote Work :

Employment Type :

Full-time

Key Skills

Dermatology
Communication
Excel
Furniture
Airlines
Jboss

Apply Now

About Company

Bosch Group

Bosch first started in Vietnam with a representative office in 1994. Bosch has its main office in Ho Chi Minh City, with branch offices in Hanoi and Da Nang, and a Powertrain Solutions plant in the Dong Nai province to manufacture pushbelt for continuously variable transmissions (CVT) ... View more

View Profile View Profile

AI AutoApply

Apply to 100+ jobs with one click