Model Selection with Nonlinear Embedding for Unsupervised Domain Adaptation

2017-06-23 · Hemanth Venkateswara, Shayok Chakraborty, Troy McDaniel, Sethuraman Panchanathan

Domain adaptation deals with adapting classifiers trained on data from a source distribution, to work effectively on data from a target distribution. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupervised domain adaptation. The NET reduces cross-domain disparity through nonlinear domain alignment. It also embeds the domain-aligned data such that similar data points are clustered together. This results in enhanced classification. To determine the parameters in the NET model (and in other unsupervised domain adaptation models), we introduce a validation procedure by sampling source data points that are similar in distribution to the target data. We test the NET and the validation procedure using popular image datasets and compare the classification results across competitive procedures for unsupervised domain adaptation.

📄 PDF Abstract BibTeX arXiv:1706.07527

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation General ClassificationModel SelectionUnsupervised Domain Adaptation

Nonlinear Embedding Transform for Unsupervised Domain Adaptation

2017-06-22 · Hemanth Venkateswara, Shayok Chakraborty, Sethuraman Panchanathan

The problem of domain adaptation (DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupe…

Domain Adaptation Unsupervised Domain Adaptation

Reinforced Domain Selection for Continuous Domain Adaptation

2025-10-12 · Hanbing Liu, Huaze Tang, Yanru Wu, Yang Li 외 arxiv

Continuous Domain Adaptation (CDA) effectively bridges significant domain shifts by progressively adapting from the source domain through intermediate domains to the target domain. However, selecting intermediate domains…

Reinforcement Learning Domain Adaptation Rotated MNIST

Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with Point Supervision via Active Selection

2022-06-01 · Fei Pan, Francois Rameau, Junsik Kim, In So Kweon

Training models dedicated to semantic segmentation requires a large amount of pixel-wise annotated data. Due to their costly nature, these annotations might not be available for the task at hand. To alleviate this proble…

Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling

2024-06-14 · Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang

In this paper, we tackle a new problem of \textit{multi-source unsupervised domain adaptation (MSUDA) for graphs}, where models trained on annotated source domains need to be transferred to the unsupervised target graph …

Domain Adaptation Meta-Learning Multi-Source Unsupervised Domain Adaptation Node Classification+1

Unsupervised Domain Adaptation with Feature Embeddings

2014-12-14 · Yi Yang, Jacob Eisenstein

Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task…

Domain Adaptation Representation Learning Unsupervised Domain Adaptation