/Student project: Self-supervised person Re-IDentification (Re-ID) with on-device learning

Student project: Self-supervised person Re-IDentification (Re-ID) with on-device learning

Research & development - Eindhoven | More than two weeks ago

The focus of this project is to build a neuromorphic sensor+processor platform that can re-identify people without direct supervision and without recording/communicating sensor data.

Student project: Self-supervised person Re-IDentification (Re-ID) with on-device learning

What you will do

In the smart office scenario, a person's Re-ID system [1] can potentially identify employees for various purposes (e.g., opening the gate for them automatically). However, preparing a properly labeled dataset of all the authorized people is cumbersome and requires regular updates. Instead, it is possible that the person's Re-ID system learns a person’s identity based on another modality (like through a password or ID card). 

An available pre-trained Re-ID neural network should be used as the starting point. On-device learning in this platform is triggered when the system’s decision is wrong or with low confidence. Therefore, its performance improves over time and adapts to the new employees and environments. 

Tasks:

  • Literature study on person Re-ID neural networks.
  • Design, optimization and implementation of the neural network for the provided neuromorphic processor[2] and the neuromorphic vision sensor[3].
  • Validation and demonstration.
  • Documentation.

Reference:
[1] Ye, Mang, et al. "Deep learning for person re-identification: A survey and outlook." IEEE Transactions on Pattern Analysis and Machine Intelligence (2021). https://arxiv.org/pdf/2001.04193.pdf 
[2] Yousefzadeh et al. “SENeCA: Scalable Energy-efficient Neuromorphic Computer Architecture”, AICAS 2022
[3] https://www.sony-semicon.co.jp/e/products/IS/industry/product/evs.html   

What we do for you

Imec is one of the world's leading research institutes in micro and nano-electronics. The work of this project will fall under the scope of a European ECSEL project ("DAIS"), and the outputs may be published in high-impact journals/conferences (subject to the quality of the work). ImecNL provides the required equipment, access to lab facilities, a workplace in the Holst Centre at High Tech Campus, and a monthly allowance during the internship. 

Who you are

  • M.Sc./Ph.D. students with a relevant background (non-European students are only eligible if they study in the Netherlands).
  • Available for 9 months (the project can be extended up to 12 months).
  • Have excellent programming skills in Python(TensorFlow/Keras) and C.
  • Are in good command of spoken and written English.
  • Motivated student, good communicator, easy collaborator, and eager to work independently and expand knowledge in the field.

Interested

Does this project sound like an interesting next step in your career at imec? Don’t hesitate to submit your application by clicking on ‘APPLY NOW’.
Should you have more questions about the project, you can contact Amirreza Yousefzadeh by mail amirreza.yousefzadeh@imec.nl.
Got some questions about the recruitment process? Marsha Loomans of the Talent Acquisition Team will be happy to assist you.