AI Paper Atlas

Research map / Detection and segmentation / CNN features

Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networks

Qianhui Liu, Haibo Ruan, Dong Xing, Huajin Tang, Gang Pan

AAAI 2020 · Detection and segmentation › CNN features · approach: Spiking event-camera detection · 68 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 SPA with peak detection instead of HOTSAER object classification · MNIST-DVSaccuracy: 80.3% -> 96.7%Improved
Use SPA with peak detection instead of Zhao's methodAER object classification · NMNISTaccuracy: 85.6% -> 96.3%Improved
Use SPA with peak detection instead of HOTSAER object classification · Cardsaccuracy: 100.0% -> 100.0%No clear effect
Use SPA with peak detection instead of HOTSAER object classification · CIFAR10-DVSaccuracy: 27.1% -> 32.2%Improved
Use SPA with peak detection instead of Zhao's methodMNIST-DVS classification · MNIST-DVS, 100 msaccuracy: 76.9% -> 89.4%Improved
Use SPA with peak detection instead of Zhao's methodMNIST-DVS classification · MNIST-DVS, 200 msaccuracy: 82.6% -> 92.7%Improved
Use SPA with peak detection instead of Zhao's methodMNIST-DVS classification · MNIST-DVS, 500 msaccuracy: 85.9% -> 94.9%Improved
Use SPA with peak detection instead of Zhao's methodMNIST-DVS classification · MNIST-DVS, Full (about 2s)accuracy: 88.1% -> 96.7%Improved
Train using informative time points in each segment rather than a single overall training pointSPA on MNIST-DVS · MNIST-DVS, first 300ms at test timeaccuracyImproved

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