Research map / Detection and segmentation / CNN features
GET: Group Event Transformer for Event-Based Vision
Yansong Peng, Yueyi Zhang, Zhiwei Xiong, Xiaoyan Sun, Feng Wu
This paper tried a common change: Add attention module
add Event Dual Self-Attention block · Cifar10-DVS · top-1 accuracy (%): 79.9 -> 81.5 Improved
What 492 accepted papers report for this change
- 444 improved
- 20 no clear effect
- 4 mixed
- 24 hurt
- Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems ICML 2026 · add wavelet attention block · CKF step 64 · Rel L2: 1.09 -> 0.35Improved
- DA-DFGAS:Differentiable Federated Graph Neural Architecture Search with Distribution-Aware Attentive Aggregation AAAI 2026 · add attention mechanism to aggregation · Table 4 datasets · parameters: about 5-10% more parametersHurt
- Caracal: Causal Architecture via Spectral Mixing ICML 2026 · add sliding window attention layers to MHF stack · Avg accuracy · avg accuracy (%): 48.22 -> 49.01Improved
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 Group Token Embedding in place of voxel-grid patch embedding (ablation) | GET (Nested-T backbone) · Cifar10-DVS | top-1 accuracy (%): 77.2 -> 79.9 | Improved |
| add Group Token Embedding in place of voxel-grid patch embedding (ablation) | GET (Nested-T backbone) · 1Mpx | mAP (%): 37.5 -> 39.1; runtime 32.1 -> 16.2 ms | Improved |
| add Event Dual Self-Attention block (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 79.9 -> 81.5 | Improved |
| add Group Token Aggregation without EDSA (ablation) | GET (Model II) · Cifar10-DVS | top-1 accuracy (%): 79.9 -> 79.4 | Hurt |
| add GTA together with EDSA (full GET) (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 81.5 -> 84.8 | Improved |
| replace Group Token with other event representations (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 84.8 vs 80.4 (TORE best alternative) | Improved |
| use dual residual EDSA block instead of serial or parallel SSA+GSA (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 81.9 -> 84.8 | Improved |
| use naive parallel SSA+GSA block instead of SSA only (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 79.4 -> 78.5 | Hurt |
| increase group number G beyond 12 on short-stream data (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 84.8 -> 82.3 -> 77.6 (G=12, 24, 48) | Hurt |
| use larger group number G=24 on long-stream data (ablation) | GET · DVS128Gesture | top-1 accuracy (%): 97.2 -> 97.9 | Improved |
| replace Swin-T v2/Nested-T modules with GET modules (token embedding, attention, aggregation) (ablation) | GET · Cifar10-DVS | top-1 accuracy (%): 80.4/81.0 -> 84.8 (aggregation) | Improved |
| add ConvLSTM memory to GET | GET · Gen1 | mAP (%): 38.7 -> 47.9 | Improved |
Closest papers by meaning
- EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection (NeurIPS 2024 · similarity 0.87)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.87)
- EventPillars: Pillar-based Efficient Representations for Event Data (AAAI 2025 · similarity 0.85)
- EventGPT: Event Stream Understanding with Multimodal Large Language Models (CVPR 2025 · similarity 0.85)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.85)
- Hybrid Spiking Vision Transformer for Object Detection with Event Cameras (ICML 2025 · 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.
