About the Ambiguity of Data Augmentation for 3D Object Detection in Autonomous Driving

Matthias Reuse, Martin Simon, Bernhard Sick

Abstract:

Although data augmentation is considered an important
step in the training strategy of 3D object detectors on point
clouds to increase the overall performance and robustness,
in almost all publications the topic of augmentation and
the choice of the individual augmentation methods used are
only addressed very briefly with reference to previous work
and are not backed up with sufficient experiments. The
question therefore arises as to the impact and the transfer-
ability of different augmentation policies. Through a se-
ries of elaborate experiments with four networks on two
datasets, this paper shows that the positive effects of dif-
ferent data augmentation methods are not so clear-cut and
instead depend strongly on the network architecture and the
dataset.