Comments (2)
Hi @Zhangjiacheng144 ,
Thanks for your attention of our work. The distillation on sigmoid probabilistic distributions can also be conducted using KL divergence loss (see Kullback–Leibler divergence, it does not require the sum of the vector to be 1). We use Equation (1) as the form of sigmoid KD loss in our RetinaNet experiments and only replace the softmax function to sigmoid.
BTW, for detectors using sigmoid focal loss, it is more practical to use the above sigmoid KL divergence loss with focal weight.
from dist_kd.
Ok, I got it, thanks for your kind reply!
from dist_kd.
Related Issues (11)
- About student checkpoint HOT 4
- bad substitution报错 HOT 7
- Releasing object detection HOT 2
- How can I reproduce the Cityscapes segmentation results HOT 5
- ModuleNotFoundError: No module named 'dataset' HOT 2
- How could I apply this KD method to other segmentation teacher/student models? HOT 2
- After the 3rd epoch it breaks down HOT 4
- How to train with custom datasets ? HOT 7
- The Segmentation of val mIoU is not 74.21 --->77.10,which is using DIST KD method based on DeepLabV3-ResNet18 HOT 5
- 关于MaskRCNN- FasterRCNN实验设置 HOT 1
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 dist_kd.