Jefersson Alex dos Santos

Jefersson Alex dos Santos

Professor of Computer Science

Universidade Federal de Minas Gerais

Hello!

I’m an Associate Professor in the Department of Computer Science at Universidade Federal de Minas Gerais, Brazil. I’m also the head and founder of the Laboratory of Pattern Recognition and Earth Observation (PATREO).

My research balances both computational challenges and their applications. Besides always aiming at excellence and impacting publications in Computer Science, I am especially interested in inter-, cross-, multidisciplinary research. I see the connection with other areas of knowledge as an opportunity to develop cutting-edge research with high possibilities for impacting directly on economic, social, and environmental aspects.

Download my resumé.

Interests
  • Computer Vision
  • Image Processing
  • Machine Learning
  • Remote Sensing
Education
  • Ph.D. in Computer Science, 2013

    Université de Cergy-Pontoise (ENSEA, France) & University of Campinas (Unicamp, Brazil)

  • M.Sc. in Computer Science, 2009

    University of Campinas (Unicamp, Brazil)

  • B.Sc. in Computer Science, 2006

    Universidade Estadual de Mato Grosso do Sul (UEMS, Brazil)

Research

My research is carried out through the activities of the Patreo laboratory. Take a look at the projects I’m currently involved as Principal Investigator:

Deep Representations for Large-Scale Geo-Mapping

Deep Representations for Large-Scale Geo-Mapping

It aims to address the problem of pattern recognition for the creation of thematic maps via supervised learning in large sets of images from small annotated data sets.

Dense Labeling of Remote Sensing Images in the Wild

Dense Labeling of Remote Sensing Images in the Wild

This project address the challenges for the effective use of supervised learning in dense pixel labeling in real-world applications by increasing the robustness of the models.

Pattern recognition using small annotated data sets

Pattern recognition using small annotated data sets

It proposes the development of new approaches to deal with the processing of large sets of images but which have restrictions regarding the number of labeled samples.

Recent Publications

Opening Deep Neural Networks with Generative Models
Learning to Segment Medical Images from Few-Shot Sparse Labels
An introduction to deep morphological networks
Fully Convolutional Open Set Segmentation

Teaching

In recent years, I have been teaching in the following courses:

  • Algorithms and Data Structures I (2016s2, 2017s1, 2018s1)
  • Deep Learning Algorithms (2019s2, 2021s2)
  • Digital Image Processing (2018s1, 2019s1)
  • Introduction to Computer Programming (2019s1, 2019s2, 2020s1, 2020s2, 2021s1)
  • Pattern Recognition for Earth Observation (2021s2)
  • Visual Pattern Recognition (2016s2, 2017s2)

Contact