Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
A
ard_poster
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Operations
Operations
Incidents
Environments
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Bui Thi Mai PHUONG
ard_poster
Commits
29defe1f
Commit
29defe1f
authored
Oct 02, 2018
by
Amelie Royer
Browse files
Options
Browse Files
Download
Plain Diff
Merge branch 'master' of git.ist.ac.at:buithimai.phuong/ard_poster
parents
db71bd39
c338bbff
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
17 additions
and
21 deletions
+17
-21
images/asya-multitask-with-theorem.pdf
images/asya-multitask-with-theorem.pdf
+0
-0
poster.tex
poster.tex
+17
-21
No files found.
images/asya-multitask-with
_
theorem.pdf
→
images/asya-multitask-with
-
theorem.pdf
View file @
29defe1f
File moved
poster.tex
View file @
29defe1f
...
...
@@ -184,41 +184,37 @@ Object categorization methods are trained to recognize \textbf{1000s of classes}
\begin{block}
{
\Large
Example: Class-incremental learning
}
\textbf
{
Situation:
}
\begin{itemize}
\item
classes appear sequentially (or in batches)
% $c_1,c_2,\dots,c_T$
\item
each class
$
y
$
has training images
$
X
^
y
=
\{
x
^
y
_
1
,
\dots
,x
^
y
_{
n
_
y
}
\}
$
\end{itemize}
\bigskip
\textbf
{
We want to/we can:
}
\begin{itemize}
\item
for any number of observed classes,
$
t
$
, learn a multi-class classifier
% for $c_1,\dots,c_t$
\item
store a certain number,
$
K
$
, of images (a few hundreds or thousands)
\end{itemize}
\begin{center}
yes
%\includegraphics{dummy} ~~
\includegraphics
[width=.5\columnwidth]
{
incremental
}
\end{center}
\bigskip
Object categorization methods are trained to recognize
\textbf
{
1000s of classes
}
:
\end{block}
\begin{block}
{
\Large
Example: Multi-task Learning
}
\begin{center}
yes
%\includegraphics{dummy} ~~
\includegraphics
[width=.5\columnwidth]
{
asya-multitask-with-theorem
}
\end{center}
\bigskip
Object categorization methods are trained to recognize
\textbf
{
1000s of classes
}
:
\end{block}
\begin{block}
{
\Large
Example: Multi-output Distillation
}
\textbf
{
Situation:
}
\begin{itemize}
\item
classes appear sequentially (or in batches)
% $c_1,c_2,\dots,c_T$
\item
each class
$
y
$
has training images
$
X
^
y
=
\{
x
^
y
_
1
,
\dots
,x
^
y
_{
n
_
y
}
\}
$
\end{itemize}
\bigskip
\textbf
{
We want to/we can:
}
\begin{itemize}
\item
for any number of observed classes,
$
t
$
, learn a multi-class classifier
% for $c_1,\dots,c_t$
\item
store a certain number,
$
K
$
, of images (a few hundreds or thousands)
\end{itemize}
\begin{center}
\includegraphics
{
multi-output/architecture.pdf
}
\end{center}
\end{block}
\end{column}
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment