Unsupervised Domain Adaptation with Adversarial Residual Transform Networks

Abstract

Domain adaptation is widely used in learning problems lacking labels. Recent studies show that deep adversarial domain adaptation models can make markable improvements in performance, which include symmetric and asymmetric architectures. However, the former has poor generalization ability whereas the latter is very hard to train. In this paper, we propose a novel adversarial domain adaptation method named Adversarial Residual Transform Networks (ARTNs) to improve the generalization ability, which directly transforms the source features into the space of target features. In this model, residual connections are used to share features and adversarial loss is reconstructed, thus making the model more generalized and easier to train. Moreover, a special regularization term is added to the loss function to alleviate a vanishing gradient problem, which enables its training process stable. A series of experiments based on Amazon review dataset, digits datasets and Office-31 image datasets are conducted to show that the proposed ARTN can be comparable with the methods of the state-of-the-art.

arXiv commentaccepted by IEEE Transactions on Neural Networks and Learning Systems

References in corpus (15)

• Distilling the Knowledge in a Neural Network
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Fully Convolutional Networks for Semantic Segmentation
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Classification with Noisy Labels by Importance Reweighting
• Marginalized Denoising Autoencoders for Domain Adaptation
• Beyond Sharing Weights for Deep Domain Adaptation
• Unsupervised Cross-Domain Image Generation
• Revisiting Batch Normalization For Practical Domain Adaptation
• Towards Principled Methods for Training Generative Adversarial Networks
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• LSDA: Large Scale Detection Through Adaptation
• The Variational Fair Autoencoder

Cited by in corpus (6)

• Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
• Learning Smooth Representation for Unsupervised Domain Adaptation
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• On the Robustness of Domain Adaption to Adversarial Attacks
• Unveiling Class-Labeling Structure for Universal Domain Adaptation
• Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint