Comments (3)
Thanks for your advice, we will add the details of the dataset settings.
from cdtrans.
We have also done experiments at the beginning, using *_train.txt samples for unlabeled data training and *_test.txt samples for testing. Later we found that the settings of the DomainNet are not consistent with the settings of other previous datasets of UDA, Office-31, Office-Home, VisDA-2017, which used the entire target sample for training and testing.
We decided to follow the setup method of other UDA datasets and use samples from the whole target domain for training and testing.
The server resources were tight at that time and the results show that it also exceeds the methods of other comparisons in this setting. So I did not run all the *_train.txt and *_test.txt experiments.
from cdtrans.
We have also done experiments at the beginning, using *_train.txt samples for unlabeled data training and *_test.txt samples for testing. Later we found that the settings of the DomainNet are not consistent with the settings of other previous datasets of UDA, Office-31, Office-Home, VisDA-2017, which used the entire target sample for training and testing. We decided to follow the setup method of other UDA datasets and use samples from the whole target domain for training and testing. The server resources were tight at that time and the results show that it also exceeds the methods of other comparisons in this setting. So I did not run all the *_train.txt and *_test.txt experiments.
Thanks for your replay! In order to avoid misleading the reader, please kindly to provide these details in the paper.
from cdtrans.
Related Issues (19)
- find HOT 2
- Questions about reproducing on VisDa
- 用于segmentation任务? HOT 1
- Single Image inference
- for row 4 of Table 5. HOT 2
- Error when training on DomainNet
- CDTrans与TransReID的关系?
- 关于主流UDA数据集的训练方法
- 关于文中主要idea在代码中的体现
- Person Reidentification
- Does the 'Baseline' in your paper mean "Deit-Base"?
- What different between 'pretrain' and 'UDA'? HOT 50
- Code problem HOT 6
- Compile error HOT 3
- Results are not consistent with the paper HOT 1
- Visualising the attention HOT 1
- DistributedDataParallel HOT 1
- Question about the Loss term in this code 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 cdtrans.