M3. Machine learning for computer vision

Machine learning deals with building solutions for the automatic analysis of large scale data, like images and video sequences. Not in the sense of writing complex, adhoc programs but algorithms able to learn to solve tasks from data. Machine learning conforms the basics of many computer vision methods, specially those related to image classification. In these days deep learning is pervasive in computer vision. As someone said, “since the breakthrough of the AlexNet network in the 2012 ImageNet classification contest, everything is deep“. In this module we update the contents in consonance. Therefore, roughly half of the module covers most important topics of “classical” machine learning biased to image classification, and the second half is an introduction to deep learning usage for computer vision.
Project title: 
Image Classification on large datasets

 The goal of this project is to learn the basic concepts of machine learning (ML) techniques for image classification, that pursuit to answer: does the image correspond to a X scene?. For this purpose, the task is to categorize in which scenario a given image was taken: ’coast’, ’forest’, ’street’, ’mountain’, . . ..The project focus on the study of different ML techniques. We will work with two different frameworks: classical Bag of Words (BoW) and Convolutional Neural Networks (CNN).  The former was the standard way of approaching the problem in the first decade of the century and it is still fundamental to understand the underlying problems that might appear in the classification task. The later, CNN, represents the new trends that have exploded in the last five years in the context of deep learning. The nature of the arising problems have shifted from the design of good hand-crafted descriptors to the development of good techniques for an efficient training of the network that learns the descriptors. In both cases the project provides practical responses on how to proceed given a task in order the student takes the best decision in designing a solution. The solution will include all the computational details and forcing to address many different alternatives to get the best performance in each case.

Module lectures: 
Academic Year 2017-2018        
Week Date Time Lecture Lecturer University Building Room
1 Mon. Dec.4th  16:00 -18:00 Introduction to machine learning. From pixels to image descriptors David Masip UAB  CVC  S. d'Actes 
1 Mon. Dec.4th  18:00 - 19:00 Project Introduction Ramon Baldrich/ Marçal Rossinyol UAB CVC  S. d'Actes
1 Wed. Dec.6th 16:00 -18:00 HOLIDAY        
               
2 Mon. Dec.11th 16:00 -18:00 Support Vector Machines    Fernando Vilariño UAB CVC S. d'Actes
2 Mon. Dec.11th 18:00 -19:00 Project  follow-up Ramon Baldrich/ Marçal Rossinyol UAB CVC  S. d'Actes 
2 Wed. Dec.13th 16:00 -18:00 Bags of words framework      Ernest Valveny UAB CVC S. d'Actes 
               
3 Mon. Dec. 18th 16:00 -18:00

Experimental setup 

Fernando Vilariño UAB CVC S. d'Actes
3 Mon. Dec. 18th 18:00 -19:00 Project follow-up Ramon Baldrich/ Marçal Rossinyol UAB CVC S. d'Actes
3

Wed. Dec. 20th 

16:00 -18:00

Introduction to Ensemble methods

 Fernando Vilariño UAB  CVC S. d'Actes 
               
      Christmas Holidays (From  Dec. 22nd  to Jan.78th)        
               
4 Mon. Jan.8th 16:00 -18:00 Introduction to deep learning  José Alvarez UAB CVC S. d'Actes
4 Mon. Jan.8th 18:00 -19:00 Project follow-up Ramon Baldrich/ David Vázquez UAB CVC S. d'Actes
4 Wed. Jan.10th  16:00 -18:00

Convolutional Neural Networks

José Alvarez UAB CVC S. d'Actes 
               
5 Mon. Jan. 15th 16:00 -18:00

Training: data pre-processing, initialization, gradient optimisation 

José Alvarez UAB CVC S. d'Actes
5 Mon. Jan. 15th 18:00 -19:00 Project follow-up Ramon Baldrich/ David Vázquez UAB CVC S. d'Actes
5 Wed. Jan. 17th 16:00 -18:00 The overfitting problem: Regularisation José Alvarez UAB CVC S. d'Actes 
               
6 Mon. Jan. 22nd 16:00 -18:00 HOMEWORK        
6 Wed. Jan. 24th 16:00 -18:00  Understanding and visualizing CNNs Ivet Rafegas UAB  CVC S. d'Actes
               
7 Mon. Jan. 29th  16:00-19:00 Project Presentations  David Vázquez      
               
8 Mon. Feb. 5th  16:00 -19:00 HOMEWORK        
8 Wed. Feb. 7th  16:00 -18:00

HOMEWORK

       
               
9 Mon. Feb. 12th 16:00 -19:00

EXAM

Joan Serrat UAB CVC S. d'Actes

M3 Student Guide [here]