Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Generalization of SELU to CNN

: Ha, Bach
: Plöger, Paul G.; Kraetzschmar, Gerhard K.; Zimmermann, Florian

Fulltext urn:nbn:de:0011-n-5407763 (1.4 MByte PDF)
MD5 Fingerprint: 41e2f844465d9636221d0e6e1ca99248
Created on: 17.4.2019

Sankt Augustin, 2019, 53 pp.
Sankt Augustin, Hochschule Bonn-Rhein-Sieg, Master Thesis, 2019
Master Thesis, Electronic Publication
Fraunhofer IAIS ()
deep learning; object detection; Batch Normalization; SELU; YOLO v3

Neural network based object detectors are able to automatize many difficult, tedious tasks. However, they are usually slow and/or require powerful hardware. One main reason is called Batch Normalization (BN) [1], which is an important method for building these detectors. Recent studies present a potential replacement called Self-normalizing Neural Network (SNN) [2], which at its core is a special activation function named Scaled Exponential Linear Unit (SELU). This replacement seems to have most of BNs benefits while requiring less computational power. Nonetheless, it is uncertain that SELU and neural network based detectors are compatible with one another. An evaluation of SELU incorporated networks would help clarify that uncertainty. Such evaluation is performed through series of tests on different neural networks. After the evaluation, it is concluded that, while indeed faster, SELU is still not as good as BN for building complex object detector networks.