Maximum Density Divergence for Domain Adaptation

by   Li Jingjing, et al.

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


page 11

page 12


Multi-step domain adaptation by adversarial attack to ℋ Δℋ-divergence

Adversarial examples are transferable between different models. In our p...

Cycle-consistent Conditional Adversarial Transfer Networks

Domain adaptation investigates the problem of cross-domain knowledge tra...

Unsupervised Domain Adaptation Based on the Predictive Uncertainty of Models

Unsupervised domain adaptation (UDA) aims to improve the prediction perf...

A DIRT-T Approach to Unsupervised Domain Adaptation

Domain adaptation refers to the problem of leveraging labeled data in a ...

Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation

Previous studies have shown that leveraging domain index can significant...

On the Metrics and Adaptation Methods for Domain Divergences of sEMG-based Gesture Recognition

We propose a new metric to measure domain divergence and a new domain ad...

Beyond ℋ-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence

We reveal the incoherence between the widely-adopted empirical domain ad...

Please sign up or login with your details

Forgot password? Click here to reset