Entropy Minimization vs. Diversity Maximization for Domain Adaptation

Abstract

Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to avoid trivial solutions by further introducing diversity maximization. In order to achieve the possible minimum target risk for UDA, we show that diversity maximization should be elaborately balanced with entropy minimization, the degree of which can be finely controlled with the use of deep embedded validation in an unsupervised manner. The proposed minimal-entropy diversity maximization (MEDM) can be directly implemented by stochastic gradient descent without use of adversarial learning. Empirical evidence demonstrates that MEDM outperforms the state-of-the-art methods on four popular domain adaptation datasets.

submitted to IEEE T-IP

References in corpus (7)

• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Domain Separation Networks
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation

Cited by in corpus (2)

• Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
• A Prototype-Oriented Framework for Unsupervised Domain Adaptation