GCN

1.视频教程：
B站、网易云课堂、腾讯课堂
2.代码地址：
Gitee
Github
3.存储地址：
Google云
百度云：
提取码：

---

• GCN-Model(pytorch版本)

---

$$为什么要用小卷积核替代大卷积核?$$

大卷积核：
优点:感受域范围大
举例:AlexNet、LeNet等网络都使用了比较大的卷积核，如5×5,11×11
缺点:参数量多;计算量大

小卷积核
优点:参数量少;计算量小;整合三个非线性激活层代替单一非线性激活层，增加模型判别能力
举例:VGG之后
缺点:感受域不足;深度堆叠卷积容易出现不可控的因素

---

• 1.一 论文导读
• 2.二 论文精读
• 3.三 代码实现
• 4.四 问题思索

《Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network》
—待写
作者：Chao Peng,etc
单位：清华大学&旷视科技
发表会议及时间：CVPR 2017

Submission history
From: Chao Peng [view email]
[v1] Wed, 8 Mar 2017 06:14:55 UTC (2,502 KB)

https://arxiv.org/abs/1703.02719

---

• Abstract
  One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity. However, in the field of semantic segmenta- tion, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive field) plays an important role when we have to perform the clas- sification and localization tasks simultaneously. Following our design principle, we propose a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation. We also suggest a residual-based boundary refinement to further refine the ob- ject boundaries. Our approach achieves state-of-art perfor- mance on two public benchmarks and significantly outper- forms previous results, 82.2% (vs 80.2%) on PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.

---

一 论文导读

二 论文精读

三 代码实现

四 问题思索