# Transferring dense object detection models to event-based data

arXiv: https://arxiv.org/abs/2210.02607 · HTML: https://mlsanity.com/paper/2210.02607/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 5 Oct 2022.

## Builds on (most cited first, 7 of 7)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Events-to-Video: Bringing Modern Computer Vision to Event Cameras](https://mlsanity.com/paper/1904.08298/) (2019)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras](https://mlsanity.com/paper/1805.07931/) (2018)

## Built on by (most cited first, 2 of 2)

- [YCB-Ev 1.1: Event-vision dataset for 6DoF object pose estimation](https://mlsanity.com/paper/2309.08482/) (2023)
- [Event-to-Video Conversion for Overhead Object Detection](https://mlsanity.com/paper/2402.06805/) (2024)

## Abstract (arXiv)

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.