Research map / Architectures and efficiency / Spiking networks
EventNet: Asynchronous Recursive Event Processing
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use EventNet instead of PointNet | ETHTED+ semantic segmentation · ETHTED+ | GA [%]: 98.9 -> 99.2 | Helped |
| Use EventNet instead of PointNet | ETHTED+ semantic segmentation · ETHTED+ | mIoU [%]: 97.4(0.13) -> 97.5(0.22) | Helped |
| Use EventNet instead of PointNet | ETHTED+ object motion · ETHTED+ | error [pix/τ]: 3.14(0.08) -> 3.11(0.28) | Helped |
| Use EventNet instead of PointNet | MVSEC ego-motion · MVSEC | error [deg/sec]: 4.55 -> 4.29 | Helped |
| Replace batch PointNet processing with EventNet's recursive event-wise processing and LUT | EventNet · 1 MEPS event processing | time per event [μs]: 953.3×10³ -> 1.01 | Helped |
| Replace mlp1/2 with a lookup table (ablation) | EventNet · 1 MEPS event processing | mlp1/2 time per event [μs]: 29.27 -> 0.65 | Helped |
| Add temporal decay (ablation) | EventNet · ETHTED+ semantic segmentation | GA [%]: 99.4 -> 99.2 | Hurt |
| Add temporal decay (ablation) | EventNet · ETHTED+ object motion | error [pix/τ]: 3.08(0.32) -> 3.11(0.28) | Helped |
| Add temporal rotation (ablation) | EventNet · ETHTED+ object motion | error [pix/τ]: 3.74(0.06) -> 3.11(0.28) | Helped |
| Add temporal decay and temporal rotation (ablation) | EventNet · ETHTED+ object motion | error [pix/τ]: 4.14(0.32) -> 3.11(0.28) | Helped |
| Add temporal decay (ablation) | EventNet · ETHTED+ semantic segmentation | mIoU [%]: 98.8(0.16) -> 97.5(0.22) | Hurt |
| Add temporal rotation (ablation) | EventNet · ETHTED+ semantic segmentation | GA [%]: 98.1 -> 99.2 | Helped |
Closest papers by meaning
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.93)
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.90)
- A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing (ICML 2025 · similarity 0.89)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.89)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.88)
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.88)
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.