CIFAR10-DVS is an event-stream dataset for object classification. 10,000 frame-based images that come from CIFAR-10 dataset are converted into 10,000 event streams with an event-based sensor, whose resolution is 128×128 pixels. The dataset has an intermediate difficulty with 10 different classes. The repeated closed-loop smooth (RCLS) movement of frame-based images is adopted to implement the conversion. Due to the transformation, they produce rich local intensity changes in continuous time which are quantized by each pixel of the event-based camera.
Source: Structure-Aware Network for Lane Marker Extraction with Dynamic Vision Sensor
Image Source: https://www.frontiersin.org/articles/10.3389/fnins.2017.00309/full
Variants: CIFAR10-DVS
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Object Recognition | Spike-VGG11 | EventRPG: Event Data Augmentation with … | 2024-03-14 |
| Object Recognition | SSNN | Shrinking Your TimeStep: Towards Low-Latency … | 2024-01-02 |
| Event data classification | OTTT | Online Training Through Time for … | 2022-10-09 |
| Event data classification | STL-SNN | A Synapse-Threshold Synergistic Learning Approach … | 2022-06-10 |
| Event data classification | tdBN + NDA (VGG11) | Neuromorphic Data Augmentation for Training … | 2022-03-11 |
| Event data classification | STS-ResNet | Convolutional Spiking Neural Networks for … | 2020-03-27 |
Recent papers with results on this dataset: