Search Results for author:
Found 9 papers, 6 papers with code
Universal Domain Adaptation from Foundation Models: A Baseline Study
We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.
Adversarial Style Augmentation for Domain Generalization
By updating the model against the adversarial statistics perturbation during training, we allow the model to explore the worst-case domain and hence improve its generalization performance.
Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization
First, we show that the key assumption of support overlap of invariant features used in IB-IRM is strong for the guarantee of OOD generalization and it is still possible to achieve the optimal solution without this assumption.
Gradual Domain Adaptation via Self-Training of Auxiliary Models
Domain adaptation becomes more challenging with increasing gaps between source and target domains.
Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques.
On Universal Black-Box Domain Adaptation
The great promise that UB$^2$DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing the interface of source model.
Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation
To make the proposed A$^2$LP useful for UDA, we propose empirical schemes to generate such virtual instances.
Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains.
Deep Metric Learning-Based Feature Embedding for Hyperspectral Image Classification
In the first task, when only a few labeled samples are available, we employ ideas from metric learning based on deep embedding features and make a similarity learning between pairs of samples.
Few-Shot Image Classification
Hyperspectral Image Classification
+3
