AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Graph-Based Object Classification for Neuromorphic Vision Sensing

Yin Bi, Aaron Chadha, Alhabib Abbas, Eirina Bourtsoulatze, Yiannis Andreopoulos

ICCV 2019 · Graph learning › Knowledge and temporal graphs · approach: Temporal graph neural architectures · 192 citations (OpenAlex)

This paper tried a common change: Add residual connections

add residual connections to plain graph CNN · N-Caltech101 · Top-1 accuracy: 0.630 -> 0.657 Improved

What 546 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
add residual connections to plain graph CNN (ablation)G-CNNs · N-Caltech101Top-1 accuracy: 0.630 -> 0.657Improved
add residual connections to plain graph CNN (ablation)G-CNNs · ASL-DVSTop-1 accuracy: 0.875 -> 0.901Improved
add residual connections to plain graph CNN (ablation)G-CNNs · MNIST-DVSTop-1 accuracy: 0.974 -> 0.986Improved
use graph representation instead of event frames with ResNet_50RG-CNNs · CIFAR10-DVSTop-1 accuracy: 0.558 -> 0.540Hurt
use graph representation instead of event frames with ResNet_50RG-CNNs · N-Caltech101GFLOPs: 3.87 -> 0.79Improved
use the SplineCNN kernel instead of MoNet graph convolutionG-CNNs · ASL-DVSTop-1 accuracy: 0.867 -> 0.875Improved
increase non-uniform sampling grid size k from 1 to 12 (ablation)G-CNNs · N-Caltech101accuracy and GFLOPs: 0.636 -> 0.612; 3.74 -> 0.26 GFLOPsMixed
increase sampling grid size k from 1 to 8 (ablation)G-CNNs · N-Caltech101accuracy and GFLOPs: 0.636 -> 0.630; 3.74 -> 0.39 GFLOPsMixed
increase graph radius R from 1.5 to 3 (ablation)G-CNNs · N-Caltech101Top-1 accuracy: 0.551 -> 0.630Improved
increase graph radius R from 3 to 6 (ablation)G-CNNs · N-Caltech101Top-1 accuracy: 0.630 -> 0.624No clear effect
lengthen event window from 10 ms to 30 ms (ablation)G-CNNs · N-Caltech101Top-1 accuracy: 0.528 -> 0.630Improved
lengthen event window from 30 ms to 70 ms (ablation)G-CNNs · N-Caltech101Top-1 accuracy: 0.630 -> 0.625No clear effect

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