
Master’s Thesis / Final-Year Project in Machine Learning and Computer Vision
Posted 4 days ago

Posted 4 days ago
This is a fully remote position, open to applicants in Germany.
• Formulate a targeted research question related to camera-based food recognition.
• Investigate and analyze existing methodologies in few-shot learning, metric learning, computer vision, and visual similarity search.
• Create and evaluate models such as DINOv2, SigLIP, as well as lightweight alternatives.
• Establish a technique for identifying new dishes using a minimal number of reference images without the need to retrain the entire model.
• Specify appropriate metrics and testing scenarios, perform experiments, and rigorously assess the outcomes.
• Collaborate with public food datasets and data derived from actual cafeteria settings.
• Examine challenges like lighting, portion sizes, tableware, and varying locations.
• Partner with the development team to translate findings into a functional prototype.
• Potential areas of focus include open-set few-shot recognition, domain shift, visually similar dishes, multi-dish recognition, and leveraging the menu as prior knowledge.
• Currently enrolled in a degree program in Computer Science, Data Science, Mathematics, or a related discipline.
• Strong foundation in machine learning, deep learning, and computer vision.
• Proficiency in Python; experience with PyTorch is a plus.
• Enthusiasm for contemporary research in computer vision.
• Ability to plan, document, and evaluate experiments in a structured manner.
• Initial experience in image classification, embeddings, transfer learning, few-shot learning, or object detection is advantageous.
• Application materials must be submitted as a single PDF, including a cover letter, resume, and certificates.
• Flexible working hours and the option for remote work.
• Part-time or full-time employment: we will tailor the working model to suit you.
• Complimentary lunch three times a week.
• An open culture with short decision-making processes and agile working methods.
• Abundant opportunities to influence your work and present ideas.
• Modern office locations in Hanover or Plauen.
• Fresh fruit, excellent coffee or tea, and a selection of beverages specific to the location.
• Regular team events and outings.
• Bike leasing options available.
• Corporate benefits.
• Company pension scheme with financial contributions toward it.
• Numerous opportunities for development and training.
• Participation in international conferences.
• Top-floor office featuring a rooftop terrace.
Memory Bridge
Entrada
Find Your Talent (FYT)
Inmetrics
Get handpicked remote jobs straight to your inbox weekly.