Transferring dense object detection models to event-based data
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Dense Object DetectionObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images
Event recognition in still images is an intriguing problem and has potential for real applications. This paper addresses the problem of event recognition by proposing a convolutional neural network that exploits knowledg…
Multi-Task LearningEvent Camera Data Dense Pre-training
This paper introduces a self-supervised learning framework designed for pre-training neural networks tailored to dense prediction tasks using event camera data. Our approach utilizes solely event data for training. Trans…
Self-Supervised LearningTransfer LearningDense Contrastive Learning for Self-Supervised Visual Pre-Training
To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-lev…
Contrastive Learningimage-classificationImage ClassificationInstance Segmentation+7WD-DETR: Wavelet Denoising-Enhanced Real-Time Object Detection Transformer for Robot Perception with Event Cameras
Previous studies on event camera sensing have demonstrated certain detection performance using dense event representations. However, the accumulated noise in such dense representations has received insufficient attention…
Denoisingobject-detectionObject DetectionReal-Time Object DetectionNo Dense Tensors Needed: Fully Sparse Object Detection on Event-Camera Voxel Grids
Event cameras produce asynchronous, high-dynamic-range streams well suited for detecting small, fast-moving drones, yet most event-based detectors convert the sparse event stream into dense tensors, discarding the repres…
Object Detection