Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

Abstract

In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the discriminator. Two problems exist with these methods. First, the domain classifier only tries to distinguish the features as a source or target and thus does not consider task-specific decision boundaries between classes. Therefore, a trained generator can generate ambiguous features near class boundaries. Second, these methods aim to completely match the feature distributions between different domains, which is difficult because of each domain's characteristics. To solve these problems, we introduce a new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries. We propose to maximize the discrepancy between two classifiers' outputs to detect target samples that are far from the support of the source. A feature generator learns to generate target features near the support to minimize the discrepancy. Our method outperforms other methods on several datasets of image classification and semantic segmentation. The codes are available at \url{https://github.com/mil-tokyo/MCD_DA}

Accepted to CVPR2018 Oral, Code is available at https://github.com/mil-tokyo/MCD_DA

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Separation Networks
• VisDA: The Visual Domain Adaptation Challenge
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Dilated Residual Networks
• Playing for Data: Ground Truth from Computer Games
• Associative Domain Adaptation

Cited by in corpus (17)

• Deep Visual Domain Adaptation: A Survey
• Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
• Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
• SPIGAN: Privileged Adversarial Learning from Simulation
• A Prototype-Oriented Framework for Unsupervised Domain Adaptation
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
• Progressive Feature Alignment for Unsupervised Domain Adaptation
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• Open Set Domain Adaptation by Backpropagation
• Angular Visual Hardness
• Adversarial Bi-Regressor Network for Domain Adaptive Regression
• Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
• Energy-constrained Self-training for Unsupervised Domain Adaptation
• DLOW: Domain Flow for Adaptation and Generalization
• Deep Transfer Learning for Infectious Disease Case Detection Using Electronic Medical Records
• Discriminative Clustering for Robust Unsupervised Domain Adaptation
• iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection