Comments (6)
可以参考“An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies”这篇文章。如果不用normalization相当于de-confound不彻底,会导致之后TDE不work,即,因为confound path的存在,所以得不到direct effect
from long-tailed-recognition.pytorch.
follow了一下,所以您是将当前观测到的样本当作是从do(x)之后的distribution中采样来的,因此给他们赋予了一个$weight = 1/P(x|M=m)$对吧?那为什么P(x|M=m) 可以近似为 L2-norm呢?这是基于什么得出的呢?
from long-tailed-recognition.pytorch.
关于怎么设计这个normalization,我们还是偏经验主义。因为Propensity Score的**只告诉我们需要对effect做balancing,但具体怎么设计其实是很开放的。
from long-tailed-recognition.pytorch.
@KaihuaTang
您好,您有试过 例如加入 circle loss ,数据不平衡的训练中加入该CausalNormClasseifer, 因为您的论文中有特征图的可视化,发现学习到的特征图更紧凑, 所以考虑 是否可以加入CausalNormClasseifer 分支 当作辅助训练,
from long-tailed-recognition.pytorch.
@KaihuaTang
您好,您有试过 例如加入 circle loss ,数据不平衡的训练中加入该CausalNormClasseifer, 因为您的论文中有特征图的可视化,发现学习到的特征图更紧凑, 所以考虑 是否可以加入CausalNormClasseifer 分支 当作辅助训练,
我没有试过,听起来好像挺靠谱的。你可以试一下看work不work
from long-tailed-recognition.pytorch.
@KaihuaTang
好的,我试一下,然后反馈一下。
我是直接加一个 CausalNormClasseifer + crosse+entropy loss, 使用它有什么超参数需要注意的吗?
from long-tailed-recognition.pytorch.
Related Issues (20)
- 关于cifar10训练精度问题 HOT 2
- 关于lvis1.0中计算d HOT 2
- Could you please provide lvis checkpoint and training log? HOT 2
- LVIS training bug: TypeError: can't pickle _thread.RLock objects HOT 2
- imagenet是2012还是2014呢? HOT 1
- imagenet-LT HOT 2
- Question about methods Cosine and Capsule in the paper HOT 3
- 请问detection中rcnn head的cls是不是做了2次softmax操作? HOT 6
- Moving average for d_hat HOT 1
- RuntimeError: Given input size: (2048x1x1). Calculated output size: (2048x-5x-5). Output size is too small HOT 1
- Migration to multi label long tailed recognition HOT 2
- Cifar Validation set HOT 1
- Focal loss on ImageNet-LT HOT 2
- 关于训练和测试集同是长尾分布时 TDE 有效性的问题? HOT 2
- 论文问题
- 关于统计移动平均特征的代码问题 HOT 1
- 论文求助
- A question regarding the assignment of num_head, tau, alpha and gamma
- Welcome update to OpenMMLab 2.0
- 一个严重的bug
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 long-tailed-recognition.pytorch.