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 2018-2019         
Week Date Time Lecture Lecturer University Building Room
1 Mon. Dec.10th  16:00 -18:00 Introduction to machine learning 1 Dimos Karatzas UAB  CVC  S. d'Actes 
1 Mon. Dec.10th  18:00 -19:00 Project Introduction: basic image classification and BOW Marçal Rossinyol  UAB   CVC   S. d'Actes  
1 Wed. Dec.12th 16:00 -18:00 Introduction to machine learning 2 D.Karatzas / Ernest Valveny UAB   CVC   S. d'Actes 
               
2 Mon. Dec.17th 16:00 -18:00 Experimental Setup / Embeddings

Fernando Vilariño

UAB CVC S. d'Actes
2 Mon. Dec.17th 18:00 -19:00 Project Introduction: basic image classification  Marçal Rossinyol UAB CVC  S. d'Actes 
2 Wed. Dec.19th 16:00 -18:00 Embedings / Case study: SVM and Random Forest Fernando Vilariño UAB CVC S. d'Actes 
               
     

Christmas Holidays

(From  Dec. 21st  to Jan. 7th)

       
               
3

Wed. Jan. 9th 

16:00 -18:00

Introduction to Deep Learning 1

 Fernando Vilariño UAB  CVC S. d'Actes 
               
4 Mon. Jan.14th 16:00 -18:00 Introduction to Deep Learning 2 Fernando Vilariño UAB CVC S. d'Actes
4 Mon. Jan.14th 18:00 -19:00 Project introduction: Deep Learning classifiers (KERAS) Ramon Baldrich UAB CVC S. d'Actes
4 Wed. Jan.16th  16:00 -18:00

Convolutional Neural Networks

Fernando Vilariño UAB CVC S. d'Actes 
               
5 Mon. Jan. 21st 16:00 -18:00

Training: data pre-processing, initialization, gradient optimisation 

Lluis Gomez UAB CVC S. d'Actes
5 Mon. Jan. 21st 18:00 -19:00 Project follow-up Ramon Baldrich UAB CVC S. d'Actes
5 Wed. Jan. 23rd 16:00 -18:00 Image Classification  Pau Rodriguez UAB CVC S. d'Actes 
               
6 Mon. Jan. 28th 16:00 -18:00 Understanding and visualizing CNNs Ivet Rafegas UAB  CVC S. d'Actes 
6 Mon. Jan. 28th 18:00 -19:00 Project follow-up  Ramon Baldrich UAB CVC S. d'Actes 
6 Wed. Jan. 30th 16:00 -18:00  Efficient methods for Deep Learning J.Carlos Moure       
               
7 Mon. Feb. 4th 16:00-19:00 Project Presentations  Ramon Baldrich UAB  CVC  S. d'Actes 
               
8 Mon. Feb. 11th  16:00 -19:00 HOMEWORK        
8 Wed. Feb. 13th  16:00 -18:00

HOMEWORK

       
               
9 Mon. Feb. 18th 16:00 -19:00

EXAM

Ramon Baldrich UAB CVC S. d'Actes
               

M3 Student Guide [here]