Research map / Detection and segmentation / Open-set and few-shot detection
N-ImageNet: Towards Robust, Fine-Grained Object Recognition With Event Cameras
Junho Kim, Jaehyeok Bae, Gangin Park, Dongsu Zhang, Young Min Kim
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 sorting to DiT (discounted timestamp image) (ablation) | DiST · N-ImageNet val | accuracy: 46.1 -> 48.43 | Improved |
| add discounting to sorted time surface (ablation) | DiST · N-ImageNet val | accuracy: 47.90 -> 48.43 | Improved |
| add sorting to DiT (ablation) | DiST · N-ImageNet variants (big trajectory change) | accuracy: 33.61 -> 35.85 | Improved |
| add discounting to sorted time surface (ablation) | DiST · N-ImageNet variants (big brightness change) | accuracy: 28.38 -> 30.88 | Improved |
| add sorting to DiT (ablation) | DiST · N-ImageNet variants (big brightness change) | accuracy: 28.42 -> 30.88 | Improved |
| pretrain on N-ImageNet instead of random initialization | ResNet34 event classifiers · N-Caltech101 | accuracy: 68.12 -> 86.81 | Improved |
| pretrain on N-ImageNet instead of ImageNet | ResNet34 event classifiers · N-Caltech101 | accuracy: 80.88 -> 86.81 | Improved |
| pretrain on N-ImageNet instead of random initialization | ResNet34 event classifiers · ASL-DVS (800 training samples) | accuracy: 29.57 -> 58.28 | Improved |
| pretrain on N-ImageNet instead of random initialization | ResNet34 event classifiers · N-Cars | accuracy: 90.80 -> 94.73 | Improved |
| pretrain on N-ImageNet instead of random initialization | ResNet34 event classifiers · CIFAR10-DVS | accuracy: 62.57 -> 73.72 | Improved |
| use relative (sorted) timestamps instead of raw timestamps | Timestamp Image · N-ImageNet val | accuracy: 45.86 -> 47.90 | Improved |
| use event counts without timestamps instead of raw timestamps | Event Histogram · N-ImageNet val | accuracy: 45.86 -> 47.73 | 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.
- HATS — HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification (CVPR 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
- Learning to Detect Objects with a 1 Megapixel Event Camera (NeurIPS 2020 · similarity 0.89)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.86)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.86)
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.86)
- LEOD: Label-Efficient Object Detection for Event Cameras (CVPR 2024 · similarity 0.86)
- Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset (CVPR 2025 · similarity 0.86)
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.
