Energy-constrained Self-training for Unsupervised Domain Adaptation

Abstract

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, and easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with the energy function minimization objective. It can be applied as a simple additional regularization. In this framework, it is possible to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. We deliver extensive experiments on the most popular and large scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.

Accepted to 25th International Conference on Pattern Recognition (ICPR 2020)

References in corpus (14)

• Learning Transferable Features with Deep Adaptation Networks
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• An introduction to domain adaptation and transfer learning
• A Theory of Generative ConvNet
• Label Refinery: Improving ImageNet Classification through Label Progression
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Implicit Generation and Generalization in Energy-Based Models
• Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
• Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
• AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation
• Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
• Unsupervised Domain Adaptation via Calibrating Uncertainties
• Conservative Wasserstein Training for Pose Estimation
• Attention Control with Metric Learning Alignment for Image Set-based Recognition