Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
arXiv:1803.09180
Abstract
Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled target domain. Unfortunately, direct transfer across domains often performs poorly due to domain shift and dataset bias. Domain adaptation is the machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain. In this paper, we summarize and compare the latest unsupervised domain adaptation methods in computer vision applications. We classify the non-deep approaches into sample re-weighting and intermediate subspace transformation categories, while the deep strategy includes discrepancy-based methods, adversarial generative models, adversarial discriminative models and reconstruction-based methods. We also discuss some potential directions.
References in corpus (9)
- Learning Transferable Features with Deep Adaptation Networks
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation
- Beyond Sharing Weights for Deep Domain Adaptation
- Adversarial Discriminative Domain Adaptation
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- Domain Generalization for Object Recognition with Multi-task Autoencoders
- Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization