A Prototype-Oriented Framework for Unsupervised Domain Adaptation
arXiv:2110.12024
Abstract
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation. Requiring no additional model parameters and having a moderate increase in computation over the source model alone, the proposed method achieves competitive performance with state-of-the-art methods.
arXiv commentNeurIPS 2021
References in corpus (20)
- Prototypical Networks for Few-shot Learning
- Learning Transferable Features with Deep Adaptation Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Temporal Ensembling for Semi-Supervised Learning
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
- Conditional Adversarial Domain Adaptation
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Model Adaptation: Unsupervised Domain Adaptation without Source Data
- A DIRT-T Approach to Unsupervised Domain Adaptation
- Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
- Universal Domain Adaptation through Self Supervision
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- On Causal and Anticausal Learning
- Self-labelling via simultaneous clustering and representation learning
- Self-ensembling for visual domain adaptation
- Support and Invertibility in Domain-Invariant Representations
- Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
- MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means
- Entropy Minimization vs. Diversity Maximization for Domain Adaptation
- Mutual Learning Network for Multi-Source Domain Adaptation