From 7bf3a3bb2bc34bf71203c9e83b6b463938bb9f37 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Wed, 20 Feb 2019 15:05:41 +0100 Subject: [PATCH] Escaped percent signs in abstract to fix compiling issues Signed-off-by: Jim Martens --- ma.bib | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ma.bib b/ma.bib index d4f4a43..6f4c1d6 100644 --- a/ma.bib +++ b/ma.bib @@ -471,7 +471,7 @@ to construct explicit models for non-normal classes. Application includes infere month = {may}, doi = {10.1109/icra.2018.8460700}, __markedentry = {[jim:1]}, - abstract = {Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks. This paper investigates the utility of Dropout Sampling for object detection for the first time. We demonstrate how label uncertainty can be extracted from a state-of-the-art object detection system via Dropout Sampling. We evaluate this approach on a large synthetic dataset of 30,000 images, and a real-world dataset captured by a mobile robot in a versatile campus environment. We show that this uncertainty can be utilized to increase object detection performance under the open-set conditions that are typically encountered in robotic vision. A Dropout Sampling network is shown to achieve a 12.3 % increase in recall (for the same precision score as a standard network) and a 15.1 % increase in precision (for the same recall score as the standard network).}, + abstract = {Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks. This paper investigates the utility of Dropout Sampling for object detection for the first time. We demonstrate how label uncertainty can be extracted from a state-of-the-art object detection system via Dropout Sampling. We evaluate this approach on a large synthetic dataset of 30,000 images, and a real-world dataset captured by a mobile robot in a versatile campus environment. We show that this uncertainty can be utilized to increase object detection performance under the open-set conditions that are typically encountered in robotic vision. A Dropout Sampling network is shown to achieve a 12.3 \% increase in recall (for the same precision score as a standard network) and a 15.1 \% increase in precision (for the same recall score as the standard network).}, file = {:/home/jim/Documents/Studium/MA/Literatur/31_dropout-sampling-for-robust-object-detection-in-open-set-conditions_miller.pdf:PDF}, owner = {jim}, timestamp = {2019.01.05},