DistanceNet is a learning algorithm for multi-source domain adaptation that uses various distance measures, or a mixture of these distance measures, as an additional loss function to be minimized jointly with the task's loss function, so as to achieve better unsupervised domain adaptation.
Source: Multi-Source Domain Adaptation for Text Classification via DistanceNet-BanditsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Classification | 1 | 16.67% |
Domain Adaptation | 1 | 16.67% |
General Classification | 1 | 16.67% |
Sentiment Analysis | 1 | 16.67% |
Text Classification | 1 | 16.67% |
Unsupervised Domain Adaptation | 1 | 16.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |