Source Hypothesis Transfer, or SHOT, is a representation learning framework for unsupervised domain adaptation. SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis.
Source: Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain AdaptationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Domain Adaptation | 3 | 25.00% |
Unsupervised Domain Adaptation | 2 | 16.67% |
Classification | 1 | 8.33% |
General Classification | 1 | 8.33% |
Object Recognition | 1 | 8.33% |
Self-Supervised Learning | 1 | 8.33% |
Partial Domain Adaptation | 1 | 8.33% |
Source-Free Domain Adaptation | 1 | 8.33% |
Universal Domain Adaptation | 1 | 8.33% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |