Maximum Density Divergence for Domain Adaptation

Abstract

Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named Adversarial Tight Match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named Maximum Density Divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations. Codes and datasets used in this paper are available at {\it github.com/lijin118/ATM}.

Published on IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

References in corpus (9)

• Conditional Generative Adversarial Nets
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• A review of domain adaptation without target labels
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• Deep Residual Correction Network for Partial Domain Adaptation

Cited by in corpus (22)

• Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
• AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation
• I2V-GAN: Unpaired Infrared-to-Visible Video Translation
• EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks
• Test-time Batch Statistics Calibration for Covariate Shift
• Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation
• ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery
• Towards Unsupervised Domain Adaptation via Domain-Transformer
• Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification
• Attention Regularized Laplace Graph for Domain Adaptation
• Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
• Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
• Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
• Memory Efficient Class-Incremental Learning for Image Classification
• Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy
• Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
• Conditional Bures Metric for Domain Adaptation
• Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation
• Domain Adaptive Semantic Segmentation without Source Data