MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation

Abstract

How to effectively learn from unlabeled data from the target domain is crucial for domain adaptation, as it helps reduce the large performance gap due to domain shift or distribution change. In this paper, we propose an easy-to-implement method dubbed MiniMax Entropy Networks (MMEN) based on adversarial learning. Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples. Specifically, we set an unfair multi-class classifier named categorical discriminator, which classifies source samples accurately but be confused about the categories of target samples. The generator learns a common subspace that aligns the unlabeled samples based on the target pseudo-labels. For MMEN, we also provide theoretical explanations to show that the learning of feature alignment reduces domain mismatch at the category level. Experimental results on various benchmark datasets demonstrate the effectiveness of our method over existing state-of-the-art baselines.

8 pages, 6 figures

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation with Residual Transfer Networks
• VisDA: The Visual Domain Adaptation Challenge
• Adversarial Discriminative Domain Adaptation
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

Cited by in corpus (3)

• Minimax Active Learning
• Jointly De-biasing Face Recognition and Demographic Attribute Estimation
• Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation