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

Unified headlines to be in title case and changed open-set to open set

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-03-07 16:43:52 +01:00
parent 3769760ab5
commit 2a95b44d8a
1 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
body_expose.tex
View File

@ -50,9 +50,9 @@ describes tasks where the network is supposed to identify the
class of any given input. In this thesis, I will focus on class of any given input. In this thesis, I will focus on
classification. classification.
\subsection*{Object detection in open-set conditions} \subsection*{Object Detection in Open Set Conditions}
More specifically, I will look at object detection in the open-set More specifically, I will look at object detection in the open set
conditions. In non-technical words this effectively describes conditions. 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
@ -108,7 +108,7 @@ auto-encoder, a novelty score is calculated. A low novelty
score signals a known object. The opposite is true for a high score signals a known object. The opposite is true for a high
novelty score. novelty score.
\subsection*{Research question} \subsection*{Research Question}
Given these two approaches to solve the explanation task of above, Given these two approaches to solve the explanation task of above,
it comes down to performance. At the end of the day the best it comes down to performance. At the end of the day the best
@ -131,14 +131,14 @@ being equal. With respect to auto-encoders a recent implementation
of an adversarial auto-encoder\cite{Pidhorskyi2018} will be used. of an adversarial auto-encoder\cite{Pidhorskyi2018} will be used.
\paragraph{Hypothesis} Novelty detection using auto-encoders \paragraph{Hypothesis} Novelty detection using auto-encoders
delivers similar or better object detection performance under open-set delivers similar or better object detection performance under open set
conditions while being less computationally expensive compared to conditions while being less computationally expensive compared to
dropout sampling. dropout sampling.
\paragraph{Contribution} \paragraph{Contribution}
The contribution of this thesis is a comparison between dropout The contribution of this thesis is a comparison between dropout
sampling and auto-encoding with respect to the overall performance sampling and auto-encoding with respect to the overall performance
of both for object detection in the open-set conditions using of both for object detection in the open set conditions using
the SSD network for object detection and the SceneNet RGB-D data set the SSD network for object detection and the SceneNet RGB-D data set
with MS COCO classes. with MS COCO classes.
@ -175,7 +175,7 @@ and intractable problem of averaging over all weights in the network
is replaced with an optimisation task, where the parameters of the is replaced with an optimisation task, where the parameters of the
simple distribution are optimised over\cite{Kendall2017}. simple distribution are optimised over\cite{Kendall2017}.
\subsubsection*{Dropout variational inference} \subsubsection*{Dropout Variational Inference}
Kendall and Gal\cite{Kendall2017} showed an approximation for Kendall and Gal\cite{Kendall2017} showed an approximation for
classfication and recognition tasks. Dropout variational inference classfication and recognition tasks. Dropout variational inference
@ -199,7 +199,7 @@ With this dropout sampling technique \(n\) model weights
of the network with respect to the classification is given by of the network with respect to the classification is given by
the entropy \(H(\mathbf{q}) = - \sum_i q_i \cdot \log q_i\). the entropy \(H(\mathbf{q}) = - \sum_i q_i \cdot \log q_i\).
\subsubsection*{Dropout sampling for object detection} \subsubsection*{Dropout Sampling for Object Detection}
Miller et al\cite{Miller2018} apply the dropout sampling to Miller et al\cite{Miller2018} apply the dropout sampling to
object detection. In that case \(\mathbf{W}\) represents the object detection. In that case \(\mathbf{W}\) represents the
@ -230,7 +230,7 @@ distribution means that no class is more likely than another, which
is a perfect example of maximum uncertainty. Conversely, if is a perfect example of maximum uncertainty. Conversely, if
one class has a very high probability the entropy will be low. one class has a very high probability the entropy will be low.
In open-set conditions it can be expected that falsely generated In open set conditions it can be expected that falsely generated
detections for unknown object classes have a higher label detections for unknown object classes have a higher label
uncertainty. A treshold on the entropy \(H(\mathbf{q}_i)\) can then uncertainty. A treshold on the entropy \(H(\mathbf{q}_i)\) can then
be used to identify and reject these false positive cases. be used to identify and reject these false positive cases.
@ -370,7 +370,7 @@ the one of dropout sampling or if the object detection performance
is worse. is worse.
\paragraph{Hypothesis} Novelty detection using auto-encoders \paragraph{Hypothesis} Novelty detection using auto-encoders
delivers similar or better object detection performance under open-set delivers similar or better object detection performance under open set
conditions while being less computationally expensive compared to conditions while being less computationally expensive compared to
dropout sampling.\\ dropout sampling.\\
@ -389,7 +389,7 @@ the thesis:
Summarising, the scientific contribution is a comparison between Summarising, the scientific contribution is a comparison between
dropout sampling and GPND with respect to both object detection dropout sampling and GPND with respect to both object detection
performance and computational performance under open-set conditions performance and computational performance under open set conditions
using the SceneNet RGB-D data set with the MS COCO classes as using the SceneNet RGB-D data set with the MS COCO classes as
"known" object classes. "known" object classes.