Research map / Detection and segmentation / CNN features
Event-based Tiny Object Detection: A Benchmark Dataset and Baseline
Nuo Chen, Chao Xiao, Yimian Dai, Shiman He, Miao Li, Wei An
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 GDSC block (ablation) | EV-SpSegNet baseline · EV-UAV test | IoU: 51.36 -> 52.73 | Improved |
| add PA block alone (ablation) | EV-SpSegNet baseline · EV-UAV test | IoU: 51.36 -> 51.26 | Hurt |
| add PA block on top of GDSC (ablation) | EV-SpSegNet · EV-UAV test | IoU: 52.73 -> 53.62 | Improved |
| add spatiotemporal correlation loss Lstc (ablation) | EV-SpSegNet baseline · EV-UAV test | IoU: 51.36 -> 53.07 | Improved |
| add Lstc to GDSC+PA model (ablation) | EV-SpSegNet · EV-UAV test | IoU: 53.62 -> 55.18 | Improved |
| add Lstc to GDSC+PA model (ablation) | EV-SpSegNet · EV-UAV test | false alarm rate: 1.93 -> 1.63 | Improved |
| use 4 GDSC branches instead of 1 (ablation) | EV-SpSegNet · EV-UAV test | IoU: 50.21 -> 55.18 | Improved |
| use 5 GDSC branches instead of 4 (ablation) | EV-SpSegNet · EV-UAV test | IoU: 55.18 -> 53.12 | Hurt |
| use larger dilation rates (1,3,5,9) instead of (1,2,3,4) (ablation) | EV-SpSegNet · EV-UAV test | IoU: 55.18 -> 51.35 | Hurt |
| add Lstc to KPConv (ablation) | KPConv · EV-UAV test | IoU: 48.19 -> 50.32 | Improved |
| add Lstc to KPConv (ablation) | KPConv · EV-UAV test | false alarm rate: 16.32 -> 10.60 | Improved |
| add Lstc to RandLA-Net (ablation) | RandLA-Net · EV-UAV test | IoU: 50.32 -> 51.15 | Improved |
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.
- Faster RCNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · 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
- M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection (NeurIPS 2026 · similarity 0.91)
- Instance Segmentation as Tracking: A New Paradigm for Multi-Small-Object Tracking with Event Cameras (ECCV 2026 · similarity 0.91)
- RemDet: Rethinking Efficient Model Design for UAV Object Detection (AAAI 2025 · similarity 0.87)
- Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras (CVPR 2025 · similarity 0.87)
- LEOD: Label-Efficient Object Detection for Event Cameras (CVPR 2024 · similarity 0.85)
- PointSR: Self-Regularized Point Supervision for Drone-View Object Detection (CVPR 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.
