35 Imaging sciences Computer vision Depth estimation Computer vision Depth

35 imaging sciences computer vision depth estimation

This preview shows page 39 - 53 out of 124 pages.

35
Image of page 39

Subscribe to view the full document.

Imaging sciences – Computer vision – Depth estimation Computer vision – Depth estimation (Stereo-vision: from two images acquired with different views.) Goal: to estimate a depth map from one, two or several frames. 36
Image of page 40
Imaging sciences – IP CV – Image colorization Image colorization (Source: Richard Zhang, Phillip Isola and Alexei A. Efros, 2016) Goal: to add color to grayscale photographs. 37
Image of page 41

Subscribe to view the full document.

Imaging sciences – IP CV – Image generation Image generation Generated images of bedrooms (Source: Alec Radford, Luke Metz, Soumith Chintala, 2015) Goal: to automatically create realistic pictures of a given category. 38
Image of page 42
Imaging sciences – IP CV – Image generation Image generation – DeepDream (Source: Google Deep Dream, Mordvintsev et al., 2016) Goal: to generate arbitrary photo - re al is tic artistic images, and understand/visualizing deep networks. 39
Image of page 43

Subscribe to view the full document.

Imaging sciences – IP CV – Image stylization Image stylization (Source: Neural Doodle, Champandard, 2016) Goal: to create stylized images from rough sketches. 40
Image of page 44
Imaging sciences – IP CV – Style transfer Style transfer (Source: Gatys, Ecker and Bethge, 2015) Goal: transfer the style of an image into another one. 41
Image of page 45

Subscribe to view the full document.

Machine learning
Image of page 46
Machine learning What is learning? Herbert Simon (Psychologist, 1916–2001): Learning is any process by which a system improves performance from experience . Pavlov’s dog (Mark Stivers, 2003) Tom Mitchell (Computer Scientist): A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P , if its performance at tasks in T, as measured by P, improves with experience E. 42
Image of page 47

Subscribe to view the full document.

Machine learning Machine learning (ML) Definition machine learning, noun : type of Artificial Intelligence that provides computers with the ability to learn without being explicitly programmed . (Source: Pedro Domingos) 43
Image of page 48
Machine learning Machine learning (ML) Provides various techniques that can learn from and make predictions on data. Most of them follow the same general structure: (Source: Lucas Masuch) 44
Image of page 49

Subscribe to view the full document.

Machine learning – Learning from examples Learning from examples 3 main ingredients 1 Training set / examples: { x 1 , x 2 , . . . , x N } 2 Machine or model: x f ( x ; θ ) | {z } function / algorithm y |{z} prediction θ : parameters of the model 3 Loss, cost, objective function / energy: argmin θ E ( θ ; x 1 , x 2 , . . . , x N ) 45
Image of page 50
Machine learning – Learning from examples Learning from examples Tools: ( Data Statistics Loss Optimization Goal: to extract information from the training set relevant for the given task, relevant for other data of the same kind. Can we learn everything? i.e. , to be relevant for all problems? 46
Image of page 51

Subscribe to view the full document.

Machine learning – No free lunch theorem No free lunch theorem (Wolpert and Macready, 1997) Any two optimization algorithms are equivalent when their performance is averaged across all possible problems.
Image of page 52
Image of page 53

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask 0 bonus questions You can ask 0 questions (0 expire soon) You can ask 0 questions (will expire )
Answers in as fast as 15 minutes