AI Paper Atlas

Research map / Detection and segmentation / CNN features

Event-based Asynchronous Sparse Convolutional Networks

Nico Messikommer, Daniel Gehrig, Antonio Loquercio, Davide Scaramuzza

ECCV 2020 · Detection and segmentation › CNN features · approach: Spiking event-camera detection · 175 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use asynchronous sparse conv instead of dense conv (histogram)VGG13 · N-Caltech101 recognitionMFLOP per event: 1621 -> 202Improved
use asynchronous sparse conv instead of dense conv (histogram)VGG13 · N-Cars recognitionMFLOP per event: 321 -> 21.5Improved
use asynchronous sparse conv instead of dense conv (histogram)VGG13 · N-Caltech101 recognitionaccuracy: 0.761 -> 0.745Hurt
use asynchronous sparse conv instead of dense conv (queue)VGG13 · N-Cars recognitionaccuracy: 0.936 -> 0.936No clear effect
use asynchronous sparse conv instead of dense conv (histogram)YOLO head · N-Caltech101 detectionmAP: 0.623 -> 0.643Improved
use asynchronous sparse conv instead of dense conv (histogram)YOLO head · Gen1 Automotive detectionmAP: 0.145 -> 0.129Hurt
use asynchronous sparse conv instead of dense conv (queue)YOLO head · Gen1 Automotive detectionmAP: 0.149 -> 0.119Hurt
use asynchronous sparse conv instead of dense conv (histogram)YOLO head · Gen1 Automotive detectionMFLOP: 2098 -> 205Improved
use 25000 events instead of 50000 for the sparse network (ablation)Sparse VGG13 · N-Caltech101 recognitionaccuracy: 0.730 -> 0.745Improved
use 25000 events instead of 5000 for the sparse network (ablation)Sparse VGG13 · N-Caltech101 recognitionaccuracy: 0.734 -> 0.745Improved
use 25000 events instead of 64 for the sparse network (ablation)Sparse VGG13 · N-Caltech101 recognitionaccuracy: 0.247 -> 0.745Improved
use 25000 events instead of 50000 for the dense network (ablation)Dense VGG13 · N-Caltech101 recognitionaccuracy: 0.761 -> 0.766No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy