Adversarial-Learned Loss for Domain Adaptation is a method for domain adaptation that combines adversarial learning with self-training. Specifically, the domain discriminator has to produce different corrected labels for different domains, while the feature generator aims to confuse the domain discriminator. The adversarial process finally leads to a proper confusion matrix on the target domain. In this way, ALDA takes the strengths of domain-adversarial learning and self-training based methods.
Source: Adversarial-Learned Loss for Domain AdaptationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Domain Adaptation | 2 | 50.00% |
Unsupervised Domain Adaptation | 1 | 25.00% |
Pseudo Label | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |