Commit d5f49efe authored by uoega's avatar uoega
Browse files

added aug table trys

parent 17f9bdd2
......@@ -26,11 +26,16 @@
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Architecture or other needed for method}}{3}{figure.1}}
\newlabel{fig:long}{{1}{3}{Architecture or other needed for method}{figure.1}{}}
\newlabel{fig:onecol}{{1}{3}{Architecture or other needed for method}{figure.1}{}}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces Unseen top-1 and top-5 accuracies results in detail.}}{3}{table.1}}
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces aug example1}}{3}{figure.2}}
\newlabel{fig:long}{{2}{3}{aug example1}{figure.2}{}}
\newlabel{fig:onecol}{{2}{3}{aug example1}{figure.2}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {3}{\ignorespaces aug example2}}{3}{figure.3}}
\newlabel{fig:long}{{3}{3}{aug example2}{figure.3}{}}
\newlabel{fig:onecol}{{3}{3}{aug example2}{figure.3}{}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces ZSL and GZSL results for different approaches.}}{3}{table.2}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}\hskip -1em.\nobreakspace {}Experiments}{3}{subsection.2.2}}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces ZSL and GZSL results for different approaches.}}{3}{table.1}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces Unseen top-1 and top-5 accuracies results in detail.}}{3}{table.2}}
\@writefile{toc}{\contentsline {section}{\numberline {3}\hskip -1em.\nobreakspace {}Results}{3}{section.3}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}\hskip -1em.\nobreakspace {}Discussion}{3}{subsection.3.1}}
\bibstyle{ieee_fullname}
\bibdata{egbib}
\bibcite{Alpher02}{1}
......@@ -38,4 +43,6 @@
\bibcite{Alpher04}{3}
\bibcite{Authors14}{4}
\bibcite{Authors14b}{5}
\@writefile{lot}{\contentsline {table}{\numberline {3}{\ignorespaces Unseen top-1 and top-5 accuracies results in detail.}}{4}{table.3}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}\hskip -1em.\nobreakspace {}Discussion}{4}{subsection.3.1}}
\@writefile{toc}{\contentsline {section}{\numberline {4}\hskip -1em.\nobreakspace {}Conclusion}{4}{section.4}}
This is pdfTeX, Version 3.14159265-2.6-1.40.19 (MiKTeX 2.9.6840 64-bit) (preloaded format=pdflatex 2018.10.16) 23 JUL 2021 16:22
This is pdfTeX, Version 3.14159265-2.6-1.40.19 (MiKTeX 2.9.6840 64-bit) (preloaded format=pdflatex 2018.10.16) 24 JUL 2021 08:53
entering extended mode
**./paper_working_design.tex
(paper_working_design.tex
......@@ -285,7 +285,20 @@ Package uniquecounter Info: New unique counter `rerunfilecheck' on input line 2
82.
)
\Hy@SectionHShift=\skip48
) (paper_working_design.aux)
) (paper_working_design.aux
LaTeX Warning: Label `fig:long' multiply defined.
LaTeX Warning: Label `fig:onecol' multiply defined.
LaTeX Warning: Label `fig:long' multiply defined.
LaTeX Warning: Label `fig:onecol' multiply defined.
)
\openout1 = `paper_working_design.aux'.
LaTeX Font Info: Checking defaults for OML/cmm/m/it on input line 25.
......@@ -303,8 +316,7 @@ LaTeX Font Info: ... okay on input line 25.
LaTeX Font Info: Checking defaults for PD1/pdf/m/n on input line 25.
LaTeX Font Info: ... okay on input line 25.
LaTeX Font Info: Try loading font information for OT1+ptm on input line 25.
("C:\Users\XPS15\AppData\Local\Programs\MiKTeX 2.9\tex\latex\psnfss\ot1ptm.fd"
("C:\Users\XPS15\AppData\Local\Programs\MiKTeX 2.9\tex\latex\psnfss\ot1ptm.fd"
File: ot1ptm.fd 2001/06/04 font definitions for OT1/ptm.
) ABD: EveryShipout initializing macros
("C:\Users\XPS15\AppData\Local\Programs\MiKTeX 2.9\tex\latex\graphics\color.sty
......@@ -446,7 +458,29 @@ Underfull \hbox (badness 10000) in paragraph at lines 121--125
[]
[3 <./Architektur.png>] (paper_working_design.bbl
Overfull \hbox (16.13214pt too wide) in paragraph at lines 129--139
[]
[]
<aug_example1.png, id=25, 1195.08984pt x 126.4725pt>
File: aug_example1.png Graphic file (type png)
<use aug_example1.png>
Package pdftex.def Info: aug_example1.png used on input line 146.
(pdftex.def) Requested size: 213.4209pt x 22.58458pt.
<aug_example2.png, id=26, 888.31876pt x 242.78203pt>
File: aug_example2.png Graphic file (type png)
<use aug_example2.png>
Package pdftex.def Info: aug_example2.png used on input line 156.
(pdftex.def) Requested size: 213.4209pt x 58.32814pt.
Underfull \vbox (badness 1533) has occurred while \output is active []
[3 <./Architektur.png> <./aug_example1.png> <./aug_example2.png>]
Underfull \vbox (badness 1325) has occurred while \output is active []
(paper_working_design.bbl
Underfull \hbox (badness 2376) in paragraph at lines 9--12
[]\OT1/ptm/m/n/9 FirstName Alpher and First-Name Fotheringham-Smythe.
[]
......@@ -457,19 +491,23 @@ Underfull \hbox (badness 1132) in paragraph at lines 14--17
[]
)
Package atveryend Info: Empty hook `BeforeClearDocument' on input line 202.
Package atveryend Info: Empty hook `BeforeClearDocument' on input line 236.
[4]
Package atveryend Info: Empty hook `AfterLastShipout' on input line 202.
Package atveryend Info: Empty hook `AfterLastShipout' on input line 236.
(paper_working_design.aux)
Package atveryend Info: Executing hook `AtVeryEndDocument' on input line 202.
Package atveryend Info: Empty hook `AtEndAfterFileList' on input line 202.
Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 202.
Package atveryend Info: Executing hook `AtVeryEndDocument' on input line 236.
Package atveryend Info: Empty hook `AtEndAfterFileList' on input line 236.
LaTeX Warning: There were multiply-defined labels.
Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 236.
)
Here is how much of TeX's memory you used:
6242 strings out of 492970
91714 string characters out of 3126593
190756 words of memory out of 3000000
10004 multiletter control sequences out of 15000+200000
6255 strings out of 492970
91935 string characters out of 3126593
192741 words of memory out of 3000000
10012 multiletter control sequences out of 15000+200000
28580 words of font info for 67 fonts, out of 3000000 for 9000
1141 hyphenation exceptions out of 8191
32i,13n,27p,1165b,324s stack positions out of 5000i,500n,10000p,200000b,50000s
......@@ -482,9 +520,9 @@ iKTeX 2.9/fonts/type1/urw/courier/ucrr8a.pfb><C:/Users/XPS15/AppData/Local/Prog
rams/MiKTeX 2.9/fonts/type1/urw/times/utmb8a.pfb><C:/Users/XPS15/AppData/Local/
Programs/MiKTeX 2.9/fonts/type1/urw/times/utmr8a.pfb><C:/Users/XPS15/AppData/Lo
cal/Programs/MiKTeX 2.9/fonts/type1/urw/times/utmri8a.pfb>
Output written on paper_working_design.pdf (4 pages, 403380 bytes).
Output written on paper_working_design.pdf (4 pages, 551837 bytes).
PDF statistics:
80 PDF objects out of 1000 (max. 8388607)
25 named destinations out of 1000 (max. 500000)
6 words of extra memory for PDF output out of 10000 (max. 10000000)
87 PDF objects out of 1000 (max. 8388607)
28 named destinations out of 1000 (max. 500000)
16 words of extra memory for PDF output out of 10000 (max. 10000000)
......@@ -124,7 +124,41 @@ To reduce the manual annotation effort, we would like to generate additional lab
{\bf Augmentation 2:} A human crouches \textit{fall} down \textit{somewhat} by bending their knees.\medskip\\
\end{quotation}
\begin{table}
\begin{center}
\begin{tabular}{|lc|}
\hline
\textbf{Description}: & A human crouches down by bending \\
& their knees. \\
\textbf{Augmentation 1:} & A \textit{small} human crouches \textit{duck} down by\\
& bending their knees.\\
\textbf{Augmentation 2:} & A human crouches \textit{fall} down \textit{somewhat}\\
& by bending their knees.\\
\hline
\end{tabular}
\end{center}
\caption{Unseen top-1 and top-5 accuracies results in detail.}
\end{table}
\begin{figure}[t]
\begin{center}
%\fbox{\rule{0pt}{2in} \rule{0.9\linewidth}{0pt}}
\includegraphics[width=0.9\linewidth]{aug_example1.png}
\end{center}
\caption{aug example1}
\label{fig:long}
\label{fig:onecol}
\end{figure}
\begin{figure}[t]
\begin{center}
%\fbox{\rule{0pt}{2in} \rule{0.9\linewidth}{0pt}}
\includegraphics[width=0.9\linewidth]{aug_example2.png}
\end{center}
\caption{aug example2}
\label{fig:long}
\label{fig:onecol}
\end{figure}
One can see, that the augmented sentences are not necessarily grammatically correct and less human readable. But as our semantic embedding is generated using a weighted average of the tokens of every word from SBERT with an attention mask, it introduces some kind of variance/diversity into the different embeddings of the descriptive labels. We expect this to perform worse compared to the three manually created descriptive label approach but still leading to some improvements compared to just using one descriptive label.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment