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
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
- 449 improved
- 35 no clear effect
- 11 mixed
- 51 hurt
- Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification ICML 2026 · add residual connection to VP · MLR-Market-1501 · Rank-1 (%): 91.2 -> 94.1Improved
- MAGIC: Multi-Granularity Language-Informed Image Clustering ICML 2026 · add residual connection to semantic adapters · CIFAR-20 · ACC: 66.1 -> 59.9Hurt
- Domain Adaptive Object Detection via Dynamic Causal Refinement ICML 2026 · add residual connection to SCC · Cityscapes to Foggy Cityscapes (0.02 split) · mAP@50: 64.0 -> 64.6Improved
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.
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add residual connections to plain graph CNN (ablation) | G-CNNs · N-Caltech101 | Top-1 accuracy: 0.630 -> 0.657 | Improved |
| add residual connections to plain graph CNN (ablation) | G-CNNs · ASL-DVS | Top-1 accuracy: 0.875 -> 0.901 | Improved |
| add residual connections to plain graph CNN (ablation) | G-CNNs · MNIST-DVS | Top-1 accuracy: 0.974 -> 0.986 | Improved |
| use graph representation instead of event frames with ResNet_50 | RG-CNNs · CIFAR10-DVS | Top-1 accuracy: 0.558 -> 0.540 | Hurt |
| use graph representation instead of event frames with ResNet_50 | RG-CNNs · N-Caltech101 | GFLOPs: 3.87 -> 0.79 | Improved |
| use the SplineCNN kernel instead of MoNet graph convolution | G-CNNs · ASL-DVS | Top-1 accuracy: 0.867 -> 0.875 | Improved |
| increase non-uniform sampling grid size k from 1 to 12 (ablation) | G-CNNs · N-Caltech101 | accuracy and GFLOPs: 0.636 -> 0.612; 3.74 -> 0.26 GFLOPs | Mixed |
| increase sampling grid size k from 1 to 8 (ablation) | G-CNNs · N-Caltech101 | accuracy and GFLOPs: 0.636 -> 0.630; 3.74 -> 0.39 GFLOPs | Mixed |
| increase graph radius R from 1.5 to 3 (ablation) | G-CNNs · N-Caltech101 | Top-1 accuracy: 0.551 -> 0.630 | Improved |
| increase graph radius R from 3 to 6 (ablation) | G-CNNs · N-Caltech101 | Top-1 accuracy: 0.630 -> 0.624 | No clear effect |
| lengthen event window from 10 ms to 30 ms (ablation) | G-CNNs · N-Caltech101 | Top-1 accuracy: 0.528 -> 0.630 | Improved |
| lengthen event window from 30 ms to 70 ms (ablation) | G-CNNs · N-Caltech101 | Top-1 accuracy: 0.630 -> 0.625 | No clear effect |
Closest papers by meaning
- Retinomorphic Object Detection in Asynchronous Visual Streams (AAAI 2022 · similarity 0.88)
- Event2Vec: Processing neuromorphic events directly by representations in vector space (ICML 2026 · similarity 0.86)
- S3Net: Spatiotemporally Separated Sparse Network for Neuromorphic Vision Processing (AAAI 2026 · similarity 0.86)
- Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networks (AAAI 2024 · similarity 0.85)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.85)
- A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing (ICML 2025 · similarity 0.83)
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.
