Domain Adaptation
Structurally Regularized Deep Clustering
Introduced by Tang et al. in Unsupervised Domain Adaptation via Structurally Regularized Deep ClusteringStructurally Regularized Deep Clustering, or SRDC, is a deep network based discriminative clustering method for domain adaptation that minimizes the KL divergence between predictive label distribution of the network and an introduced auxiliary one. Replacing the auxiliary distribution with that formed by ground-truth labels of source data implements the structural source regularization via a simple strategy of joint network training.
Source: Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Clustering | 1 | 25.00% |
| Deep Clustering | 1 | 25.00% |
| Domain Adaptation | 1 | 25.00% |
| Unsupervised Domain Adaptation | 1 | 25.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
