Open-Set Object Detection: Can VLM understand all of the unknown world? H/F

Vacancy details

General information

Organisation

The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas :
• defence and security,
• nuclear energy (fission and fusion),
• technological research for industry,
• fundamental research in the physical sciences and life sciences.

Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners.

The CEA is established in ten centers spread throughout France
  

Reference

2024-33175  

Description de l'unité

Based in Saclay (Essonne), the LIST is one of the two institutes of CEA Tech, the Technological Research Division of the CEA. Dedicated to intelligent digital systems, its mission is to carry out technological developments of excellence on behalf of industrialpartners, in order to create value. Within the LIST, the Laboratory of Vision and Learning for Scene Analysis (LVA) conducts its research in the field of computer visionand artificial intelligence for the perception of intelligent and autonomous systems. The laboratory's research themes include visual recognition, behavior and activity analysis, large-scale automatic annotation, and perception and decision models.

Position description

Category

Mathematics, information, scientific, software

Contract

Internship

Job title

Open-Set Object Detection: Can VLM understand all of the unknown world? H/F

Subject

Deep learning models have demonstrated significant success to detect a close set of known annotated classes seen during training. But, how will they behave when facing up to objects of unknown classes?
As their behaviour is uncertain when subjected to never-before-seen classes, we aim to develop robust Open Set ObjectDetectors (OSOD), able to localise and classify any objects, no matter their classes are known or unknown during training.
It is of paramount importance to ensure safe deployment of AI models as trustable AI is crucial in critical applications such as autonomous driving. Indeed, one of the most important issues for these applications is the lack of supervisory signals on data notseen in training, which can generate erroneous yet confident predictions on out-of-distribution (OOD) data.

Contract duration (months)

6

Job description

Your missions within this internship are to:

• Study state-of-the-art methods of Open Set Object Detection (OSOD) as well as Visual Language Models (VLM) in the context of Open World containing both known and unknown objects;

• Design an object detector aware of the existence of the unknown;

• Evaluate the proposed method on recent OSOD benchmarks and compare to the state of the art;

• Challenge these methods by applying them to new contexts (e.g. aerial images);

• If relevant, submit your contributions to an international conference or workshop for publication.

Methods / Means

Computer vision, deep learning, VLM, pytorch

Applicant Profile

Join CEA List and LVA as an intern to:

• Work in one of the most innovative research organizations in the world, addressing societal challenges to build the world of tomorrow

• Discover a rich ecosystem: privileged connections between the industrial and academic sectors

• Conduct research autonomously and creatively: encouragement to valorize results (scientific articles, patents, open-source codes...)

• Join a young and dynamic team

• Benefit from an internal computing infrastructure with more than 300 state-of-the-art GPUs

• Receive a stipend between €1300 and €1400 per month

• Have the opportunity to continue with a PhD or as aresearch engineer after the internship

• Have the possibility of remote work, receive a 75% reimbursement on public transportation costs, and benefitfrom the “mobili-jeune”aid to reduce rent costs..

 

In line with CEA's commitment to integrating people with disabilities, this job is open to all.

Position location

Site

Saclay

Job location

France, Ile-de-France, Essonne (91)

Location

Palaiseau

Candidate criteria

Prepared diploma

Bac+5 - Master of Science

Recommended training

Master / école d'ingénieur en computer vision / AI

PhD opportunity

Oui

Requester

Position start date

01/02/2025