Research map / Architectures and efficiency / Spiking networks
MENet: A Memory-Based Network with Dual-Branch for Efficient Event Stream Processing
Linhui Sun, Yifan Zhang, Ke Cheng, Jian Cheng, Hanqing Lu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add adjustment component (ablation) | MENet · DVS128 Gesture | accuracy %: 97.34 -> 98.86 | Improved |
| add point-wise memory bank (ablation) | MENet · DVS128 Gesture | accuracy %: 96.96 -> 98.86 | Improved |
| use double polarities calculation instead of Sub-diff (ablation) | MENet · DVS128 Gesture | accuracy %: 97.34 -> 98.86 | Improved |
| add memory bank to single-branch model (ablation) | Single-nomem · MNIST-DVS | accuracy %: 98.8 -> 99.57 | Improved |
| add memory bank to single-branch model (ablation) | Single-nomem · N-Cars | accuracy %: 93.4 -> 95.32 | Improved |
| add incremental branch to MENet-single (ablation) | MENet-single · DVS128 Gesture | accuracy %: 98.11 -> 98.86 | Improved |
| add incremental branch to MENet-single (ablation) | MENet-single · DVS128 Gesture | GFLOPs: 4.73 -> 2.00 | Improved |
| use incremental branch instead of base branch per window (ablation) | MENet · DVS128 Gesture | time per window (ms): 288 -> 15 | Improved |
| increase Nwin from 4 to 12 (ablation) | MENet · DVS128 Gesture | accuracy %: 98.86 -> 94.31 | Hurt |
| increase Nwin from 2 to 4 (ablation) | MENet · DVS128 Gesture | accuracy %: 98.11 -> 98.86 | Improved |
| increase Nwin from 4 to 6 (ablation) | MENet · DVS128 Gesture | accuracy %: 98.86 -> 98.48 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Slayer — SLAYER: Spike Layer Error Reassignment in Time (NeurIPS 2018) · better on 1 of 1 shared result
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
- EventNet: Asynchronous Recursive Event Processing (CVPR 2019 · similarity 0.89)
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.86)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.86)
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.86)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.86)
- EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection (NeurIPS 2024 · similarity 0.85)
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.
