Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

# Unsupervised domain adaptation via double classifiers based on high confidence pseudo label

11 May 2021

In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution.

# Aggregating From Multiple Target-Shifted Sources

9 May 2021

Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain.

# More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation

7 May 2021

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation.

# Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation

5 May 2021

To avoid the costly annotation of training data for unseen domains, unsupervised domain adaptation (UDA) attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain.

# Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation

5 May 2021

To align the conditional distributions, we further develop an easy-to-hard pseudo label refinement process to improve the quality of the pseudo labels and then reduce categorical spherical manifold Gaussian kernel geodesic loss.

# Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks

28 Apr 2021

This network can achieve source to target domain matching by capturing semantic information at the feature level and producing images for unsupervised domain adaptation from both the source and the target domains.

# Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery

28 Apr 2021

Modern deep neural networks (DNNs) achieve highly accurate results for many recognition tasks on overhead (e. g., satellite) imagery.

# Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

27 Apr 2021

Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited.

# STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains

23 Apr 2021

We propose to predict the uncertainty of pseudo labels and integrate it in the training process with an uncertainty-guided loss function to highlight labels with high certainty.

# Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval

18 Apr 2021

In this paper, we propose a new domain adaptation method called $\textit{back-training}$, a superior alternative to self-training.