Über diesen Kurs
50,049

100 % online

Beginnen Sie sofort und lernen Sie in Ihrem eigenen Tempo.

Flexible Fristen

Setzen Sie Fristen gemäß Ihrem Zeitplan zurück.

Stufe „Fortgeschritten“

Ca. 25 Stunden zum Abschließen

Empfohlen: 5 weeks of study...

Englisch

Untertitel: Englisch, Koreanisch

100 % online

Beginnen Sie sofort und lernen Sie in Ihrem eigenen Tempo.

Flexible Fristen

Setzen Sie Fristen gemäß Ihrem Zeitplan zurück.

Stufe „Fortgeschritten“

Ca. 25 Stunden zum Abschließen

Empfohlen: 5 weeks of study...

Englisch

Untertitel: Englisch, Koreanisch

Lehrplan - Was Sie in diesem Kurs lernen werden

Woche
1
3 Stunden zum Abschließen

Introduction to image processing and computer vision

Welcome to the "Deep Learning for Computer Vision“ course! In the first introductory week, you'll learn about the purpose of computer vision, digital images, and operations that can be applied to them, like brightness and contrast correction, convolution and linear filtering. These simple image processing methods solve as building blocks for all the deep learning employed in the field of computer vision. Let’s get started!...
8 Videos (Gesamt 54 min), 2 Quiz
8 Videos
Digital images3m
Structure of human eye and vision6m
Color models15m
Image processing goals and tasks2m
Contrast and brightness correction5m
Image convolution7m
Edge detection8m
1 praktische Übung
Basic image processing10m
Woche
2
4 Stunden zum Abschließen

Convolutional features for visual recognition

Module two revolves around general principles underlying modern computer vision architectures based on deep convolutional neural networks. We’ll build and analyse convolutional architectures tailored for a number of conventional problems in vision: image categorisation, fine-grained recognition, content-based retrieval, and various aspect of face recognition. On the practical side, you’ll learn how to build your own key-points detector using a deep regression CNN. ...
12 Videos (Gesamt 91 min), 2 Quiz
12 Videos
AlexNet, VGG and Inception architectures11m
ResNet and beyond10m
Fine-grained image recognition5m
Detection and classification of facial attributes6m
Content-based image retrieval7m
Computing semantic image embeddings using convolutional neural networks8m
Employing indexing structures for efficient retrieval of semantic neighbors9m
Face verification6m
The re-identification problem in computer vision5m
Facial keypoints regression6m
CNN for keypoints regression5m
1 praktische Übung
Convolutional features for visual recognition24m
Woche
3
3 Stunden zum Abschließen

Object detection

In this week, we focus on the object detection task — one of the central problems in vision. We start with recalling the conventional sliding window + classifier approach culminating in Viola-Jones detector. Tracing the development of deep convolutional detectors up until recent days, we consider R-CNN and single shot detector models. Practice includes training a face detection model using a deep convolutional neural network....
13 Videos (Gesamt 46 min), 2 Quiz
13 Videos
Sliding windows3m
HOG-based detector2m
Detector training3m
Viola-Jones face detector5m
Attentional cascades and neural networks3m
Region-based convolutional neural network3m
From R-CNN to Fast R-CNN5m
Faster R-CNN4m
Region-based fully-convolutional network2m
Single shot detectors3m
Speed vs. accuracy tradeoff1m
Fun with pedestrian detectors1m
1 praktische Übung
Object Detection16m
Woche
4
4 Stunden zum Abschließen

Object tracking and action recognition

The fourth module of our course focuses on video analysis and includes material on optical flow estimation, visual object tracking, and action recognition. Motion is a central topic in video analysis, opening many possibilities for end-to-end learning of action patterns and object signatures. You will learn to design computer vision architectures for video analysis including visual trackers and action recognition models....
11 Videos (Gesamt 74 min), 2 Quiz
11 Videos
Optical flow5m
Deep learning in optical flow estimation5m
Visual object tracking5m
Examples of visual object tracking methods13m
Multiple object tracking5m
Examples of multiple object tracking methods8m
Introduction to action recognition6m
Action classification7m
Action classification with convolutional neural networks5m
Action localization6m
1 praktische Übung
Video Analysis16m
Woche
5
3 Stunden zum Abschließen

Image segmentation and synthesis

In the last module of this course, we shall consider problems where the goal is to predict entire image. These are semantic image segmentation and image synthesis problems. Modern CNNs tailored for segmentation employ multiple specialised layers to allow for efficient training and inference. Lastly, we will get to know Generative Adversarial Networks — a bright new idea in machine learning, allowing to generate arbitrary realistic images....
7 Videos (Gesamt 43 min), 2 Quiz
7 Videos
Oversegmentation4m
Deep learning models for image segmentation7m
Human pose estimation as image segmentation8m
Style transfer5m
Generative adversarial networks7m
Image transformation with neural networks5m
1 praktische Übung
Image segmentation and synthesis14m
3.9
29 BewertungenChevron Right

Top-Bewertungen

von SJJun 12th 2018

Excellent course! Quiz questions are conceptual and challenging and assignments are pretty rigorous and 100% practical application oriented.

von RRApr 19th 2019

Don't just read what's written on the projector. Try explaining it. And explain with code.

Dozenten

Avatar

Anton Konushin

Senior Lecturer
HSE Faculty of Computer Science
Avatar

Alexey Artemov

Senior Lecturer
HSE Faculty of Computer Science

Über National Research University Higher School of Economics

National Research University - Higher School of Economics (HSE) is one of the top research universities in Russia. Established in 1992 to promote new research and teaching in economics and related disciplines, it now offers programs at all levels of university education across an extraordinary range of fields of study including business, sociology, cultural studies, philosophy, political science, international relations, law, Asian studies, media and communicamathematics, engineering, and more. Learn more on www.hse.ru...

Über die Spezialisierung Erweiterte maschinelles Lernen

This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings....
Erweiterte maschinelles Lernen

Häufig gestellte Fragen

  • Sobald Sie sich für ein Zertifikat angemeldet haben, haben Sie Zugriff auf alle Videos, Quizspiele und Programmieraufgaben (falls zutreffend). Aufgaben, die von anderen Kursteilnehmern bewertet werden, können erst dann eingereicht und überprüft werden, wenn Ihr Unterricht begonnen hat. Wenn Sie sich den Kurs anschauen möchten, ohne ihn zu kaufen, können Sie womöglich auf bestimmte Aufgaben nicht zugreifen.

  • Wenn Sie sich für den Kurs anmelden, erhalten Sie Zugriff auf alle Kurse der Spezialisierung und Sie erhalten nach Abschluss aller Arbeiten ein Zertifikat. Ihr elektronisches Zertifikat wird zu Ihrer Seite „Errungenschaften“ hinzugefügt – von dort können Sie Ihr Zertifikat ausdrucken oder es zu Ihrem LinkedIn Profil hinzufügen. Wenn Sie nur lesen und den Inhalt des Kurses anzeigen möchten, können Sie kostenlos als Gast an dem Kurs teilnehmen.

Haben Sie weitere Fragen? Besuchen Sie das Hilfe-Center für Teiln..