Primary tabs

Tuesday, November 23, 2021

All day
 
 
Before 01
01
02
03
04
05
06
07
08
09
10
11
12
13
14
15
16
17
18
19
20
21
22
23
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Lecture
“Deep Internal learning” -- Deep Learning and Visual inference without prior examples
11/23/2021
14:18

“Deep Internal learning” -- Deep Learning and Visual inference without prior examples

Prof. Michal Irani | Dept of Computer Science and Applied Mathematics, WIS

Tue, Nov 23, 12:30 | Gerhard M.J. Schmidt Lecture Hall

In the first part of my talk I will show how complex visual inference tasks can be performed with Deep-Learning, in a totally unsupervised way, by training on a single image -- the test image alone. The strong recurrence of information inside a single natural image provides powerful internal examples which suffice for self-supervision of Deep-Networks, without any prior examples or training data. This new paradigm gives rise to true “Zero-Shot Learning”. I will show the power of this approach to a variety of visual tasks, including super-resolution, image-segmentation, transparent layer separation, image-dehazing, and more. In the second part of my talk I will show how self-supervision can be used for “Mind-Reading” (recovering observed visual information from fMRI brain recordings), when only very few fMRI training examples are available.