Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation

Abstract

We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct classifiers with them. We propose a novel approach that jointly learn the both. Specifically, while the method identifies a feature space where data in the source and the target domains are similarly distributed, it also learns the feature space discriminatively, optimizing an information-theoretic metric as an proxy to the expected misclassification error on the target domain. We show how this optimization can be effectively carried out with simple gradient-based methods and how hyperparameters can be cross-validated without demanding any labeled data from the target domain. Empirical studies on benchmark tasks of object recognition and sentiment analysis validated our modeling assumptions and demonstrated significant improvement of our method over competing ones in classification accuracies.

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

References in corpus (2)

• Domain Adaptation for Statistical Classifiers
• Domain Adaptation: Learning Bounds and Algorithms

Cited by in corpus (26)

• A review of domain adaptation without target labels
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Small Sample Learning in Big Data Era
• Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network
• Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
• ConDA: Continual Unsupervised Domain Adaptation
• Semi-Generative Modelling: Covariate-Shift Adaptation with Cause and Effect Features
• Cross-Domain Visual Recognition via Domain Adaptive Dictionary Learning
• Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
• Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction
• TLR: Transfer Latent Representation for Unsupervised Domain Adaptation
• Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint
• More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
• Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces
• Discriminative Density-ratio Estimation
• Contrastive Representations for Label Noise Require Fine-Tuning
• On-target Adaptation
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
• Unsupervised Domain Adaptation: A Reality Check
• Conceptual Domain Adaptation Using Deep Learning