Publikationen

Autor	Mechler, Vinzenz; Rojtberg, Pavel
Datum	2023
Art	Conference Paper
Abstrakt	Event-based image representations are fundamentally different to traditional dense images. This poses a challenge to apply current state-of-the-art models for object detection as they are designed for dense images. In this work we evaluate the YOLO object detection model on event data. To this end we replace dense-convolution layers by either sparse convolutions or asynchronous sparse convolutions which enables direct processing of event-based images and compare the performance and runtime to feeding event-histograms into dense-convolutions. Here, hyper-parameters are shared across all variants to isolate the effect sparse-representation has on detection performance. At this, we show that current sparse-convolution implementations cannot translate their theoretical lower computation requirements into an improved runtime.
Konferenz	International Conference on Artificial Intelligence and Virtual Reality 2022
ISBN	978-981-19-7742-8
Publisher	Springer
Url	https://publica.fraunhofer.de/handle/publica/437903

Transferring Dense Object Detection Models to Event-Based Data