Comments (5)
Hi @XiaoxxWang, our PPC loss takes the form of InfoNCE, which is in essence a cross-entropy loss. In our context, you can understand PPC as, for each pixel, we aim to identify its assigned (positive) prototype among a set of negative prototypes.
I also have a question, the PPC code does not seem to reflect the temperature coefficient setting? Or is the temperature coefficient set to 1 by default, which is different from the 0.1 given in the paper?
from protoseg.
Hi @XiaoxxWang, our PPC loss takes the form of InfoNCE, which is in essence a cross-entropy loss. In our context, you can understand PPC as, for each pixel, we aim to identify its assigned (positive) prototype among a set of negative prototypes.
from protoseg.
Thanks for your reply, but I still can't understand the PPC loss well. The code shows it is defined as the cross entropy of the proto_logits with proto_targets. The proto_logits is the product of the feature and the prototype, but what does proto_targets mean? It seems it is not the groundtruth , which is not agree with infoNCE loss.
from protoseg.
@XiaoxxWang Just read the code more carefully... For, InforNCE, you also have the groundtruth -- you know which one is the positive sample, and which one is the negative sample, but the ground-truth is obtained by free.
from protoseg.
The temperature coefficient In paper is set as 0.1, howerver, in the source code it is neglected. In other words, it is set to 1 by default in source code. Does it have no influnce for the performance ?
from protoseg.
Related Issues (20)
- When will the code be released?
- Question about the prototype initialization? HOT 2
- Question about code HOT 5
- parameter numbers of the entire model? HOT 2
- Questions about code HOT 1
- Question about paper [# model parameter] HOT 6
- Question about Within-Class Online Clustering HOT 8
- Questions about K prototypes HOT 1
- Question regarding IoUs of pretrained HRNet Proto HOT 3
- Question about seed HOT 3
- Layernorm in Prototype learning HOT 1
- Please how to continue training on the previous model, setting --resume_continue y does not take effect
- How long is the speed of each picture in the model test?
- intra-class prototypes is same. HOT 2
- Can't run the code because of dims
- awesome work!
- Question about the existence of the normalization, and how to run it
- Initial Prototype
- 'ce_weight' parameter in loss
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 protoseg.