Semi supervised object detection

Deep learning technology is a great tool to learn complex patterns and make prediction based on this learning. In order to get the most accurate predictions, one needs to train those neural networks on vast amount of labelled data. Labelling data is a time consuming and costly task. Using semi supervised learning, it should be possible to label a fraction of the dataset and let the neural network learn by itself on the rest of the, unlabelled, data, thus greatly reducing the overhead of using deep learning technology. This project aims at identifying and implementing the best possible semi supervised strategy for object detection.

Faculty Supervisor:

Ioannis Mitliagkas

Student:

Partner:

Teledyne DALSA Semiconducteur (Montreal, QC)

Discipline:

Computer science

Sector:

Manufacturing

University:

Université de Montréal

Program: