Generative Adversarial Networks for Domain Adaptation between synthetic and real images



Learning from as little human supervision as possible is a major challenge in Machine Learning. In the context of computer vision, Deep Learning is a class of supervised learning algorithms that require a great amount of human-labeled images in order to be trained [1]. An opportunity to reduce the needed amount of human labeling is offered by synthetic dataset, where the labeling procedure comes at almost no cost. The problem with the introduction of synthetic datasets is the domain gap with real images ones.

Generative Adversarial Networks (GANs) [2, 3] are a class of deep neural networks able to generate synthetic data with the same distribution of a target dataset. They have been applied to very different areas with excellent results, from the generation of realistic face images to 3d points cloud [4].

The aim of this thesis is to study the possibility of using GAN to cover the domain gap between real and synthetic images [5]. The objective is to develop an algorithm that minimizes the amount of labeled real data needed to train a target deep neural network while obtaining the best classification accuracy.

Planned Activities

  1. Acquire strong knowledge about the most recent DNN architectures and training procedures;
  2. Acquire strong knowledge about the GAN models and their application to transform synthetic images to real ones
  3. Conduct extended experiments on real-synthetic dataset pairs and analyzing the improvements and drawbacks of the domain adaptation approach based on GANs
  4. Duration of this Project: 5-6 months.The candidate will acquire:
    • Expertise on Deep Learning;
    • Expertise on Computer Vision;
    • Experience about the training of most recent GAN models and architectures.

Who we’re looking for

Students that are about to get their Master Degree in mathematical engineering or computer science or computer engineering or electronic engineering or mathematics or physics or physics of complex systems.

Required Skills:

  • Proficiency in at least one programming language (Python, Lua, Matlab, C++, Java);
  • Basic knowledge of machine learning, in particular, supervised learning;
  • Good knowledge of linear algebra.

Check these links before moving on

Contact Us