giteahh
8273017082
- Add 8 PARA directories to .gitignore whitelist (234 files) - Completes dual-layer sync: LLM Wiki layer + PARA personal knowledge layer - markdown_output/ remains excluded (transit zone)
170 lines
2.5 KiB
Markdown
170 lines
2.5 KiB
Markdown
---
|
||
marp: "true"
|
||
theme: university-blue
|
||
paginate: "true"
|
||
footer: XX大学 · 计算机科学学院
|
||
author: [你的姓名]
|
||
date: 2026-04-08
|
||
---
|
||
|
||
<!-- _class: cover -->
|
||
<!-- _paginate: false -->
|
||
|
||
# {论文题目}
|
||
|
||
### {姓名} · 导师：{导师姓名}
|
||
|
||
{专业} · {毕业类型} · {年份}
|
||
|
||
---
|
||
|
||
## 目录
|
||
|
||
1. 研究背景与意义
|
||
2. 相关工作
|
||
3. 方法设计
|
||
4. 实验结果
|
||
5. 总结与展望
|
||
|
||
---
|
||
|
||
<!-- _class: trans -->
|
||
|
||
## 一、研究背景与意义
|
||
|
||
---
|
||
|
||
### 研究背景
|
||
|
||
- {背景要点1}
|
||
- {背景要点2}
|
||
- {背景要点3}
|
||
|
||
### 研究意义
|
||
|
||
> 提出一种{核心技术}，提升{关键指标}的性能。
|
||
|
||
---
|
||
|
||
<!-- _class: trans -->
|
||
|
||
## 二、相关工作
|
||
|
||
---
|
||
|
||
### 传统方法
|
||
|
||
- 方法 A：{描述}
|
||
- 方法 B：{描述}
|
||
- 局限性：{说明}
|
||
|
||
### 深度学习方法
|
||
|
||
- 方法 C：{描述}
|
||
- 方法 D：{描述}
|
||
- 本研究切入点
|
||
|
||
---
|
||
|
||
<!-- _class: trans -->
|
||
|
||
## 三、方法设计
|
||
|
||
---
|
||
|
||
### 整体框架
|
||
|
||
```python
|
||
class Model(nn.Module):
|
||
def __init__(self):
|
||
super().__init__()
|
||
self.backbone = ResNet50()
|
||
self.attention = AttentionBlock()
|
||
self.classifier = nn.Linear(2048, num_classes)
|
||
|
||
def forward(self, x):
|
||
features = self.backbone(x)
|
||
attended = self.attention(features)
|
||
return self.classifier(attended)
|
||
```
|
||
|
||
### 核心创新
|
||
|
||
1. {创新点1}
|
||
2. {创新点2}
|
||
3. {创新点3}
|
||
|
||
---
|
||
|
||
## 四、实验结果
|
||
|
||
### 数据集
|
||
|
||
| 数据集 | 训练集 | 测试集 | 类别数 |
|
||
|---------|---------|---------|--------|
|
||
| Dataset1 | 10K | 2K | 100 |
|
||
| Dataset2 | 50K | 10K | 1000 |
|
||
|
||
### 性能对比
|
||
|
||
| 方法 | Dataset1 | Dataset2 | 平均精度 |
|
||
|------|-----------|-----------|---------|
|
||
| Baseline | 84.2% | 91.3% | 87.8% |
|
||
| Method A | 86.1% | 92.8% | 89.5% |
|
||
| **Ours** | **89.3%** | **94.6%** | **92.0%** |
|
||
|
||
> [!note] 本方法在所有数据集上均取得了最优结果。
|
||
|
||
---
|
||
|
||
<!-- _class: cols-2 -->
|
||
|
||
## 五、总结与展望
|
||
|
||
<div class="ldiv">
|
||
|
||
### 主要贡献
|
||
|
||
- ✅ 提出了{方法}
|
||
- ✅ 在{数据集}上达到 SOTA
|
||
- ✅ 代码已开源
|
||
|
||
</div>
|
||
|
||
<div class="rdiv">
|
||
|
||
### 未来工作
|
||
|
||
- 🔜 扩展到{新任务}
|
||
- 🔜 探索{新技术}
|
||
- 🔜 在{新领域}验证
|
||
|
||
</div>
|
||
|
||
---
|
||
|
||
<!-- _class: dark -->
|
||
|
||
### 关键发现
|
||
|
||
1. {发现1}
|
||
2. {发现2}
|
||
3. {发现3}
|
||
|
||
---
|
||
|
||
<!-- _class: ending -->
|
||
<!-- _paginate: false -->
|
||
|
||
# 谢谢！
|
||
|
||
### 欢迎提问与讨论
|
||
|
||
---
|
||
|
||
## 参考文献
|
||
|
||
1. [Author1], "Paper Title", Journal, 2020.
|
||
2. [Author2], "Paper Title", Conference, 2021.
|
||
3. [Author3], "Paper Title", ArXiv, 2022.
|