M5. Visual recognition

In this module we give to the student an overview of the latest methods based on deep learning techniques to solve visual recognition problems. The final aim is the understanding of complex scenes to build feasible systems for automatic image understanding able to answer the complex question of what objects and where are these objects in a complex scene. The students will learn a large family of successful architectures of deep convolutional networks that have been proved to solve the visual tasks of: detection, segmentation and recognition. And they are going to get the skills for designing, programming, training and evaluating complex architectures to solve vision problems.
Project title: 
Scene Understanding for automatic driving

The goal of this project is to learn the basic concepts and techniques to build deep neural networks to detect, segment and recognize specific objects, focusing on images recorded by an on-board vehicle camera for autonomous driving. 

The learning objectives are using different deep learning (DL) programming frameworks such Theano, TensorFlow and Keras and  basic DL methods such as feed forward networks (MLP) and  Convolutional  Neural Networks (CNN). It includes the understanding of standard networks for classification (AlexNet, VGG, GoogleNet, ResNet, DenseNet, SqueezeNet) detection (RCNN, Fast RCNN, Faster RCNN, YOLO) and segmentation (FCN, SegNet, UNET).  The students will learn through a project based methodology using modern collaborative tools at all stages of the project development.

The students will acquire the skills for the tasks of designing, training, tuning and evaluating neural networks to solve the problem of automatic image understanding.

Module lectures: 

Academic Year 2020-2021 

M5 Student Guide [here]

       
Week Date Time Lecture Lecturer University Building Room
1 Mon. Mar. 1st 16:00 - 18:00 Object Detection 1 LLuis Gómez UAB CVC  
1 Mon. Mar. 1st 18:00 - 19:00  Introduction to the M5 project E. Valveny / A.F. Biten / A. Mafla UAB CVC  
1 Wed. Mar. 3rd 16:00 - 18:00 Object Detection 2 LLuis Gómez UAB CVC  
               
2 Mon. Mar. 8th 16:00 - 18:00 Semantic and Instance Segmentation 1 David Vázquez UAB CVC  
2 Mon. Mar. 8th 18:00 - 19:00 Project Introduction: Object Detection 1 E. Valveny / A.F. Biten / A. Mafla UAB CVC   
2 Wed. Mar. 10th 16:00 - 18:00 Semantic and Instance Segmentation 2 David Vázquez UAB CVC  
               
3 Mon. Mar. 15th 16:00 - 18:00 Metric Learning Joan Serrat UAB CVC  
3 Mon. Mar. 15th 18:00 - 19:00 Project follow-up: Object Detection 2 E. Valveny / A.F. Biten / A. Mafla UAB CVC  
3 Wed. Mar. 17th 16:00 - 18:00  Multimodal Deep Learning* Luís Herranz  UAB  CVC  
               
4 Mon. Mar. 22nd 16:00 -18:00 Transfer Learning Petia Radeva UAB CVC  
4 Mon. Mar. 22nd 18:00 -19:00 Project follow-up: Object Detection 3 E. Valveny / A.F. Biten / A. Mafla UAB CVC  
4 Wed. Mar. 24th 16:00 -18:00 Graph Networks*  Adriana Romero    UAB CVC  
               
5 Mon. Mar. 23rd 16:00 -18:00  Easter Holidays  (from March. 29th to Apr. 5th)

               

     
               
6 Mon. Apr. 7th 16:00 -18:00 Architectures for Image Generation (GANs & VAEs) 1 Michal Drozdzal                  UAB  CVC  
               
7 Mon. Apr. 12th 16:00 -18:00 Architectures for Image Generation (GANs & VAEs) 2 Michal Drozdzal   UAB  CVC  
7 Mon. Apr. 12th 18:00 -19:00 Project follow-up: Semantic Segmentation 1 E. Valveny / A.F. Biten / A. Mafla UAB  CVC  
7 Wed. Apr. 14th 16:00 -18:00 Reinforcement Learning Adriana Romero         
               
8 Wed. Apr. 19th   16:00 -19:00  

Project presentations

E. Valveny / A.F. Biten / A. Mafla UAB  CVC    
               
9 Mon. Apr. 26th   HOMEWORK        
9 Wed. Apr. 28th   HOMEWORK Adriana Romero       
               
10

Mon. May. 3rd

16:00 -19:00 EXAM Joan Serrat UAB CVC Sala d'Actes
               

M5 Student Guide [here]