Comments (1)
Thank you for raising these questions.
-
Among the two filtering conditions,
conf_u_w_cutmixed2 >= cfg['conf_thresh']
is for selecting high-confidence pseudo labels, whileignore_mask_cutmixed2 != 255
is to avoid the loss computation in padded regions from image pre-processing. And we only divide the second conditiontorch.sum(ignore_mask_cutmixed2 != 255).item()
in the third line, because we hope((conf_u_w_cutmixed2 >= cfg['conf_thresh']) & (ignore_mask_cutmixed2 != 255)).sum() / (ignore_mask_cutmixed2 != 255).sum()
can serve as an adaptive weight for our unsupervised loss. Concretely, at earlier training stages, the adaptive weight will be small, due to the abundant low-confidence pixels. Our model is mainly learned with labeled images. Then as training proceeds, the adaptive weight will gradually increase to learn more on unlabeled images. You may also refer to the Equation 2 in FixMatch. -
I think that either 0.5 or 0.95 is just a hyperparameter, regardless of the number of classes. In your case of binary classification, I guess you may use a sigmoid function for classification. Then you can still maintain a 0.95 threshold by only considering the output > 0.95 (certainly class 1) and the output < 0.05 (certainly class 0). The 0.5 you mentioned probably denotes the classification threshold for sigmoid, rather than our confidence threshold.
-
I think the unsupervised loss weight can be adjusted according to your observations. It may depend on the proportion and hardness of unlabeled images.
from unimatch.
Related Issues (20)
- 关于医学图像分割场景下的结果 HOT 4
- Image-level Perturbations in LEVIR HOT 1
- Pascal Voc 数据集的checkpoint HOT 19
- 关于特征空间扰动 HOT 4
- 关于第四页的Algorithm 1 HOT 2
- Question about the batch size
- Reproducability of PASCAL VOC HQ dataset results HOT 4
- 关于在Transformer系列模型使用 HOT 2
- Can't find Resnet 101
- How much memory its necessary? HOT 1
- 轻量级backbone及训练问题 HOT 1
- Question about crop size HOT 2
- 关于sliding_window HOT 1
- 复现训练代码
- 256×256的分辨率需要多少的GPU运行内存 HOT 1
- 评估和可视化代码 HOT 2
- color_map function in the utils.py file HOT 1
- Minor Typo HOT 1
- 关于split的问题 HOT 1
- 关于您该项目的实验 HOT 3
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 unimatch.