Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation

Abstract

Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain features that are divergent from source-domain features. However, by optimizing via such domain classification discrepancy, ambiguous target samples that are not smoothly distributed on the low-dimensional data manifold are often missed. To solve this issue, we propose a novel Contrastively Smoothed Class Alignment (CoSCA) model, that explicitly incorporates both intra- and inter-class domain discrepancy to better align ambiguous target samples with the source domain. CoSCA estimates the underlying label hypothesis of target samples, and simultaneously adapts their feature representations by optimizing a proposed contrastive loss. In addition, Maximum Mean Discrepancy (MMD) is utilized to directly match features between source and target samples for better global alignment. Experiments on several benchmark datasets demonstrate that CoSCA can outperform state-of-the-art approaches for unsupervised domain adaptation by producing more discriminative features.

References in corpus (16)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Learning Transferable Features with Deep Adaptation Networks
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Domain Separation Networks
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Triple Generative Adversarial Nets
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• Co-regularized Alignment for Unsupervised Domain Adaptation
• Contrastive Learning for Image Captioning
• Adversarial Dropout Regularization
• Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach

Cited by in corpus (3)

• Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis
• Joint Contrastive Learning for Unsupervised Domain Adaptation
• Domain Agnostic Learning for Unbiased Authentication