2martens/masterthesis-latex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Updated decoding pipeline for Bayesian SSD

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-08-27 15:39:15 +02:00
parent 98d57633ff
commit 3360cb0315
1 changed files with 11 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
body.tex
View File

@ -57,7 +57,7 @@ conditions (see figure \ref{fig:open-set}).
In non-technical words this effectively describes In non-technical words this effectively describes
the kind of situation you encounter with CCTV cameras or robots the kind of situation you encounter with CCTV cameras or robots
outside of a laboratory. Both use cameras that record outside of a laboratory. Both use cameras that record
images. Subsequently a neural network analyses the image images. Subsequently, a neural network analyses the image
and returns a list of detected and classified objects that it and returns a list of detected and classified objects that it
found in the image. The problem here is that networks can only found in the image. The problem here is that networks can only
classify what they know. If presented with an object type that classify what they know. If presented with an object type that
@ -69,7 +69,7 @@ such a network would falsely assume that a high confidence always
means the classification is very likely correct. If they use means the classification is very likely correct. If they use
a proprietary system they might not even be able to find out a proprietary system they might not even be able to find out
that the network was never trained on a particular type of object. that the network was never trained on a particular type of object.
Therefore it would be impossible for them to identify the output Therefore, it would be impossible for them to identify the output
of the network as false positive. of the network as false positive.
This goes back to the need for automatic explanation. Such a system This goes back to the need for automatic explanation. Such a system
@ -78,7 +78,7 @@ hence mark any classification result of the network as meaningless.
Technically there are two slightly different approaches that deal Technically there are two slightly different approaches that deal
with this type of task: model uncertainty and novelty detection. with this type of task: model uncertainty and novelty detection.
Model uncertainty can be measured with dropout sampling. Model uncertainty can be measured, for example, with dropout sampling.
Dropout is usually used only during training but Dropout is usually used only during training but
Miller et al.~\cite{Miller2018} use them also during testing Miller et al.~\cite{Miller2018} use them also during testing
to achieve different results for the same image making use of to achieve different results for the same image making use of
@ -143,19 +143,12 @@ passes is varied to identify their impact.
delivers better object detection performance under open set delivers better object detection performance under open set
conditions compared to object detection without it. conditions compared to object detection without it.
\paragraph{Contribution}
The contribution of this thesis is a comparison between dropout
sampling and auto-encoding with respect to the overall performance
of both for object detection in the open set conditions using
the SSD network for object detection and the SceneNet RGB-D data set
with MS COCO classes.
\subsection*{Reader's guide} \subsection*{Reader's guide}
First, chapter \ref{chap:background} presents related works and First, chapter \ref{chap:background} presents related works and
provides the background for dropout sampling a.k.a Bayesian SSD. provides the background for dropout sampling a.k.a Bayesian SSD.
Afterwards, chapter \ref{chap:methods} explains how the Bayesian SSD Afterwards, chapter \ref{chap:methods} explains how the Bayesian SSD
works, and provides details about the software and source code design. works and how the decoding pipelines are structured.
Chapter \ref{chap:experiments-results} presents the data sets, Chapter \ref{chap:experiments-results} presents the data sets,
the experimental setup, and the results. This is followed by the experimental setup, and the results. This is followed by
chapter \ref{chap:discussion} and \ref{chap:closing}, focusing on chapter \ref{chap:discussion} and \ref{chap:closing}, focusing on
@ -473,7 +466,7 @@ image across multiple forward passes.
\subsection{Implementation Details} \subsection{Implementation Details}
For this thesis, an SSD implementation based on Tensorflow and For this thesis, an SSD implementation based on Tensorflow~\cite{Abadi2015} and
Keras\footnote{\url{https://github.com/pierluigiferrari/ssd\_keras}} Keras\footnote{\url{https://github.com/pierluigiferrari/ssd\_keras}}
was used. It was modified to support entropy thresholding, was used. It was modified to support entropy thresholding,
partitioning of observations, and dropout partitioning of observations, and dropout
@ -554,8 +547,11 @@ to the following shape of the network output after all
forward passes: \((batch\_size, \#nr\_boxes \, \cdot \, \#nr\_forward\_passes, \#nr\_classes + 12)\). The size of the output forward passes: \((batch\_size, \#nr\_boxes \, \cdot \, \#nr\_forward\_passes, \#nr\_classes + 12)\). The size of the output
increases linearly with more forward passes. increases linearly with more forward passes.
These detections have to be decoded first. Afterwards they are These detections have to be decoded first. Afterwards,
partitioned into observations to reduce the size of the output, and all detections are thrown away which do not pass a confidence
threshold for the class with the highest prediction probability.
The remaining detections are partitioned into observations to
further reduce the size of the output, and
to identify uncertainty. This is accomplished by calculating the to identify uncertainty. This is accomplished by calculating the
mutual IOU of every detection with all other detections. Detections mutual IOU of every detection with all other detections. Detections
with a mutual IOU score of 0.95 or higher are partitioned into an with a mutual IOU score of 0.95 or higher are partitioned into an
@ -575,8 +571,7 @@ varying classifications are averaged into multiple lower confidence
values which should increase the entropy and, hence, flag an values which should increase the entropy and, hence, flag an
observation for removal. observation for removal.
Per class confidence thresholding, non-maximum suppression, and The final step is a top \(k\) selection.
top \(k\) selection happen like in vanilla SSD.
\chapter{Experimental Setup and Results} \chapter{Experimental Setup and Results}