Comments (1)
Hello,
Thanks for your interest in our paper.
- There exist some fluctuations in performance, so I encourage you to perform multiple runs.
- The main contribution of our paper is how to avoid negative transfer by selectively search positive source samples. The experiment result also justifies that our approach could achieve competitive results with about 1K source images.
- The pool_prop is designed to minimize the pool size for source selection. We found that, employing 20% of source samples randomly, already enables our selection criterion to find positive samples. You surely could disable such a random process, which means you need to enumerate the whole source set (24996 images).
- About the motivation of our source selection, I encourage you to refer to our paper for more details.
from ccm.
Related Issues (14)
- Source only model HOT 4
- Baseline_model HOT 1
- config, writer = init_config("config/final_config.yml", sys.argv) HOT 1
- neptune.exceptions.MissingApiToken: Missing API token. HOT 2
- thres in gene_thres HOT 1
- Source Only Train HOT 1
- self.cnts don't need to be updated? HOT 1
- Could you provide the pre-trained model "SYNTHIA-Source-only"
- A little question about piece of code in the ccm_config.yml HOT 2
- Questions about the two models HOT 2
- Training error: RuntimeError: For non-complex input tensors, argument alpha must not be a complex number. HOT 7
- about the label of target domain HOT 1
- About SYNTHIA pretrained models
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 ccm.