Transferring dense object detection models to event-based data
This work addresses a challenge in computer vision for researchers working with event-based sensors, but it is incremental as it focuses on evaluating existing methods without introducing new paradigms.
The authors tackled the problem of applying dense object detection models to event-based data by evaluating YOLO with sparse convolutions, finding that current sparse-convolution implementations do not achieve improved runtime despite theoretical advantages.
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.