MaFewShot

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Meta-Learning in Medical Imaging

Supervision: Prof. Dr. Nassir Navab, Dr. Shadi Albarqouni

Abstract

Medical Image classification has become competitive with human experts, in some domains. However, its success seems contingent on the availability of large bodies of annotated data; and it is often difficult and expensive to acquire such datasets. High data requirements are a general issue in modern Deep Learning, and increasing sample efficiency is one of the fundamental research problems today. Meta-learning is one of the directions taken to alleviate the need for huge datasets via learning to learn. The goal of this project is to build on work presented in (Snell et al. 2917; Finn et al. 2017) to find approaches to image classification which are sample efficient and adaptable to Semi-Supervised Learning.

Requirements:

  • Good understanding of statistics and machine learning methods.
  • Very good programming skills in Python & TensorFlow? / PyTorch?

Location:

  • Garching

Literature

Resultant Paper

A. Ayyad, N. Navab, M. Elhoseiny, S. Albarqouni
Semi-Supervised Few-Shot Learning with Local and Global Consistency
Submitted to the 36th International Conference on Machine Learning.
A pre-print version is available online at arXiv.
(bib)

ProjectForm
Title: Meta-Learning in Medical Imaging
Abstract: Medical Image classification has become competitive with human experts, in some domains. However, its success seems contingent on the availability of large bodies of annotated data; and it is often difficult and expensive to acquire such datasets. High data requirements are a general issue in modern Deep Learning, and increasing sample efficiency is one of the fundamental research problems today. Meta-learning is one of the directions taken to alleviate the need for huge datasets via learning to learn. The goal of this project is to build on work presented in (Snell et al. 2917; Finn et al. 2017) to find approaches to image classification which are sample efficient and adaptable to Semi-Supervised Learning.
Student: Ahmed Ayad
Director: Prof. Dr. Nassir Navab
Supervisor: Dr. Shadi Albarqouni
Type: IDP
Area: Machine Learning, Medical Imaging, Computer Vision
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.4 - 16 Mar 2019 - 22:11 - ShadiAlbarqouni