Deep Learning for Computer Vision

  • Type: Vorlesung (V)
  • Semester: SS 2018
  • Time: 2018-04-16
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten


    2018-04-23
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-04-30
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-05-07
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-05-14
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-05-28
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-06-04
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-06-11
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-06-18
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-06-25
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-07-02
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-07-09
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten

    2018-07-16
    11:30 - 13:00 wöchentlich
    50.34 Raum -101 50.34 INFORMATIK, Kollegiengebäude am Fasanengarten


  • Lecturer: Prof. Dr.-Ing. Rainer Stiefelhagen
    Dr.-Ing. Muhammad Saquib Sarfraz
  • SWS: 2
  • Lv-No.: 24628
Comment

Basic knowledge of pattern recognition as taught in the module Cognitive Systems is expected.

Content of teaching

The lecture introduces the basics, as well as advanced aspects of deep learning methods and their application for a number of computer vision tasks. The following topics will be addressed in the lecture:

- Introduction to Deep Learning

- Convolutional Neural Networks (CNN): Background

- CNNs: basic architectures and learning algorithms

- Object Recognition with CNN

- Image Segmentation with CNN

- Recurrent Neural Networks

- Generating image descriptions (Image Captioning)

- Automatic question answering (Visual Question Answering)

- Generative Adversarial Networks (GAN) and their applications

- Deep Learning platforms and tools

Annotation

The lecture is partially given in German and English.

Shortdescription

In recent years tremendous progress has been made in analysing and understanding image and video content. The dominant approach in Computer Vision today are deep learning approaches, in particular the usage of Convolutional Neural Networks.

Workload

90 Stunden

Aim

Students should be able to grasp the underlying concepts in the field of deep learning and its various applications.

  • Understand the theoretical basis of deep learning
  • Understand the Convolutional Neural Networks (CNN)
  • Develop basis for the concepts and algorithms used in building and training the CNNs.
  • Able to apply deep learning in different computer vision applications
Exam description

Die Erfolgskontrolle erfolgt in Form einer mündlichen Prüfung im Umfang von i.d.R. 20 Minuten nach § 4 Abs. 2 Nr. 2 SPO.

Vorlesungsfolien

16.04.2018      Introduction / Overview [pdf]

23.04.2018      Neural Networks - Basics [pdf]

30.04.2018      No lecture

07.05.2018      Deep CNN Networks Background [pdf]

14.05.2018      CNN Architectures [pdf]

21.05.2018      Feiertag (no lecture)

28.05.2018      Object Detection and Segmentation [pdf]

04.06.2018      Recurrent Neural Networks (RNN) and Embeddings [pdf]

11.06.2018      RNNs for Image Caption / Tagging [pdf]

18.06.2018      Visual Question-Answering (VQA) [pdf]

25.06.2018      CNN Learing in Videos [pdf]

02.07.2018      General Adversial Networks (GAN) [pdf]

09.07.2018      Deep Learngin Frameworks & Tools [pdf]

16.07.2018      Summary [pdf]