Comments (5)
Hello @HanqingXu ,
Sorry for the late response. In some sense, the two aforementioned losses play as regularization terms to bring "adaptation effect" to the final model. Their weighting factors are indeed sensitive to the particular adaptation setting. Normally we cross-validate to choose the proper weighting values. Regarding the direct entropy loss concern, it is possible that the model gets "corrupted" as you described, especially when using too big entropy weight. Pre-training only on the source domain might mitigate such adverse effects. However, as we use unsupervised losses on the target samples, there is no good guarantee to avoid the corrupted scenario. Again, there is no magic hyper-parameters that work for all cases, you will need to cross-validate to find the good set.
T-H
from advent.
Thank your for the reply. I tried the entropy loss term in my dataset. For the direct loss, even if I tried tuning the weighting factor, it still hurts the performance. As for the adversarial loss, it doesn't even converge. I saw several methods from your paper and try weighting the unsupervised loss, and training on specific ranges. Neither worked. Any suggestios would be appreciated.
from advent.
Can you specify which dataset and which task you are working on?
from advent.
I tried the KITTI dataset which has only 200 images (which was my intention since I want it to fully exploit the advantage of the domain adaptation), and my own private dataset which is lane marking dataset(8 classes) in some parking lot. It has only around 200 as well
from advent.
Ok I see. It's actually difficult to give you suggestions on a set-up that we've never seen. Maybe some guidelines for you: - make sure that your baseline performance on the target set (no UDA) is "OKish", - pretrain the model without UDA only on source. - do more data augmentation as your datasets are quite small.
T-H
from advent.
Related Issues (20)
- How to implement from SYNTHIA to Cityscapes? HOT 3
- Could you please release the code of painting entropy maps? HOT 3
- Could you release the code related to detection DA? HOT 2
- Training Performance and Stability HOT 3
- Class ratio prior loss ? HOT 1
- reproducibility of the results
- About pre-trained model HOT 1
- Hyperparameters for training with CycleGAN translated images
- How to perform ensembling?
- question about the segmentation network HOT 1
- source_label=0; target_label=1
- Direct entropy minimization for object detection (YOLOv3)
- Data normalization before feeding to the Segmentation network HOT 1
- binary segmentation
- Is it typing error? (at loss function)
- How to visualize segmentation results “soft-segmentation map”? HOT 1
- One hot encoding
- 目标域中没有train的标签时,代码报错
- Why doesn't the output shape of the discriminator have to be (B,1,1,1)?
- IS DeepLab_resnet_pretrained_imagenet.pth pretrained on Source data?
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 advent.