Comments (2)
@Asthestarsfalll
非常高兴看到我们的方法对你的模型有提升,也感谢你很有insight的分析。有一点我可能还是需要澄清一下:
其他的都是对空间上某一个或几个部分注意的更多,这显然是存在偏颇的
我觉得其他频率也并没有对某些部分注意更多,因为DCT的基函数都是由cos wave构成的,所以他是非常对称的一种结构。而且他是预先数学上定义好的形式,是data-independent的,所以我觉得可能没有过分关注某个部分这种情况。至于为什么GAP效果最好,我觉得可能有两个原因吧,第一个是求平均确实很好的一种提取信息的方式,也对微小变化不是很敏感(这个有可能对于抽象,提高语义理解能力是很有帮助的)。第二个是神经网络似乎就是喜欢低频一些,这个可以在CVPR2020那篇 learning in the frequency domain 找到佐证。
其他的观点我还是比较认同的,是有可能在上述方案中取得更好的效果的。
from fcanet.
@cfzd
好的,感谢您的答复让我发现了频率在神经网络中的神奇奥秘!
另外,我将映射大小改为8,频率分量的选取改为
mapper_x = [0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 7, 0]
mapper_y = [0, 1, 2, 3, 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0, 0]
相较于原FCA模块获得了0.3的提升,不过也可能是实验误差。
from fcanet.
Related Issues (20)
- SE-NET基础上加FCA HOT 1
- 关于 the L73-L83 in model/layer.py 中learnable tensor的问题 HOT 2
- 低频分量 HOT 2
- selecting frequency components HOT 1
- 请问YOLOX可以使用吗?看到是ResNet? HOT 1
- model.init HOT 1
- 想请问一下代码中bot是怎么选取的代表什么意思 HOT 1
- get_dct_weights() cannot be found HOT 3
- 是否能提供一下对比实验中ResNet50的结果权重呢? HOT 2
- dct_h and dct_w HOT 5
- 关于模型精度 HOT 2
- 这个不是和SeNet差不多吗?为啥不可以做成即插即用的注意力模块
- 频率分量的确定 HOT 4
- 如何理解和解释,固定的DCT比可学习的方式更好? HOT 2
- 如何进行FcaNet-TS的实验 HOT 3
- 关于7X7频域的问题 HOT 4
- 一维的GAP是否可以被视为一维DCT的特例呢
- Implementation MultiSpectralAttentionLayer in Tensorflow
- 修改为三维
- 关于特定频率分量的选择
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fcanet.