Update README.md

README.md

@@ -1,3 +1,166 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- ILSVRC/imagenet-1k
+- uoft-cs/cifar10
+- uoft-cs/cifar100
+language:
+- en
+metrics:
+- accuracy
+base_model:
+- MS-ResNet
+---
+
+<div align="center">
+
+<h1>I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks</h1>
+
+[![Paper](https://img.shields.io/badge/Arxiv-2511.08065-B31B1B.svg)](https://arxiv.org/abs/2511.08065)
+[![AAAI 2026](https://img.shields.io/badge/AAAI%202026-Oral-4b44ce.svg)](https://aaai.org/)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/Ruichen0424/I2E)
+
+</div>
+
+## 🚀 Introduction
+
+This repository contains the **pre-trained weights** for the paper **"I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks"**, which has been accepted for **Oral Presentation at AAAI 2026**.
+
+**I2E** is a pioneering framework that bridges the data scarcity gap in neuromorphic computing. By simulating microsaccadic eye movements via highly parallelized convolution, I2E converts static images into high-fidelity event streams in real-time (>300x faster than prior methods).
+
+### ✨ Key Highlights
+* **SOTA Performance**: Achieves **60.50%** top-1 accuracy on Event-based ImageNet.
+* **Sim-to-Real Transfer**: Pre-training on I2E data enables **92.5%** accuracy on real-world CIFAR10-DVS, setting a new benchmark.
+* **Real-Time Conversion**: Enables on-the-fly data augmentation for deep SNN training.
+
+## 🏆 Model Zoo & Results
+
+We provide pre-trained models for **I2E-CIFAR** and **I2E-ImageNet**. You can download the `.pth` files directly from the **Files and versions** tab in this repository.
+
+<table>
+    <tr>
+        <th>Target Dataset</th>
+        <th align="center">Architecture</th>
+        <th align="center">Method</th>
+        <th align="center">Top-1 Acc</th>
+    </tr>
+    <!-- CIFAR10-DVS -->
+    <tr>
+        <td rowspan="3" align="center" style="vertical-align: middle;"><strong>CIFAR10-DVS</strong><br>(Real)</td>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline</td>
+        <td align="center">65.6%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Transfer-I</td>
+        <td align="center">83.1%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Transfer-II (Sim-to-Real)</td>
+        <td align="center"><strong>92.5%</strong></td>
+    </tr>
+    <!-- I2E-CIFAR10 -->
+    <tr>
+        <td rowspan="3" align="center" style="vertical-align: middle;"><strong>I2E-CIFAR10</strong></td>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline-I</td>
+        <td align="center">85.07%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline-II</td>
+        <td align="center">89.23%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Transfer-I</td>
+        <td align="center"><strong>90.86%</strong></td>
+    </tr>
+    <!-- I2E-CIFAR100 -->
+    <tr>
+        <td rowspan="3" align="center" style="vertical-align: middle;"><strong>I2E-CIFAR100</strong></td>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline-I</td>
+        <td align="center">51.32%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline-II</td>
+        <td align="center">60.68%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Transfer-I</td>
+        <td align="center"><strong>64.53%</strong></td>
+    </tr>
+    <!-- I2E-ImageNet -->
+    <tr>
+        <td rowspan="4" align="center" style="vertical-align: middle;"><strong>I2E-ImageNet</strong></td>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline-I</td>
+        <td align="center">48.30%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Baseline-II</td>
+        <td align="center">57.97%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet18</td>
+        <td align="center">Transfer-I</td>
+        <td align="center">59.28%</td>
+    </tr>
+    <tr>
+        <td align="center">MS-ResNet34</td>
+        <td align="center">Baseline-II</td>
+        <td align="center"><strong>60.50%</strong></td>
+    </tr>
+</table>
+
+> **Method Legend:**
+> * **Baseline-I**: Training from scratch with minimal augmentation.
+> * **Baseline-II**: Training from scratch with full augmentation.
+> * **Transfer-I**: Fine-tuning from Static ImageNet (or I2E-ImageNet for CIFAR targets).
+> * **Transfer-II**: Fine-tuning from I2E-CIFAR10.
+
+## 👁️ Visualization
+
+Below is the visualization of the I2E conversion process. We illustrate the high-fidelity conversion from static RGB images to dynamic event streams.
+
+<div align="center">
+  <img src="./assets/original_1.jpg" width="22%" alt="Original RGB Image 1">
+  <img src="./assets/converted_1.gif" width="22%" alt="Converted Event Stream 1">
+  <img src="./assets/original_2.jpg" width="22%" alt="Original RGB Image 2">
+  <img src="./assets/converted_2.gif" width="22%" alt="Converted Event Stream 2">
+</div>
+<div align="center">
+  <img src="./assets/original_3.jpg" width="22%" alt="Original RGB Image 3">
+  <img src="./assets/converted_3.gif" width="22%" alt="Converted Event Stream 3">
+  <img src="./assets/original_4.jpg" width="22%" alt="Original RGB Image 4">
+  <img src="./assets/converted_4.gif" width="22%" alt="Converted Event Stream 4">
+</div>
+
+## 💻 Usage & Datasets
+
+This repository hosts the **model weights only**.
+
+For the **I2E dataset generation code**, **training scripts**, and detailed usage instructions, please refer to our official GitHub repository:
+
+👉 **[GitHub: Ruichen0424/I2E](https://github.com/Ruichen0424/I2E)**
+
+To generate the datasets (I2E-CIFAR10, I2E-CIFAR100, I2E-ImageNet) yourself using the I2E algorithm, please follow the instructions in the GitHub README.
+
+## 📜 Citation
+
+If you find this work or the models useful, please cite our AAAI 2026 paper:
+
+```bibtex
+@article{ma2025i2e,
+  title={I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks},
+  author={Ma, Ruichen and Meng, Liwei and Qiao, Guanchao and Ning, Ning and Liu, Yang and Hu, Shaogang},
+  journal={arXiv preprint arXiv:2511.08065},
+  year={2025}
+}
+```