A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
arXiv:2009.00155
Abstract
Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and 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 or unlabeled target domain. Unfortunately, direct transfer across domains often performs poorly due to the presence of domain shift or dataset bias. Domain adaptation is a 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 review the latest single-source deep unsupervised domain adaptation methods focused on visual tasks and discuss new perspectives for future research. We begin with the definitions of different domain adaptation strategies and the descriptions of existing benchmark datasets. We then summarize and compare different categories of single-source unsupervised domain adaptation methods, including discrepancy-based methods, adversarial discriminative methods, adversarial generative methods, and self-supervision-based methods. Finally, we discuss future research directions with challenges and possible solutions.
References in corpus (47)
- Auto-Encoding Variational Bayes
- Overcoming catastrophic forgetting in neural networks
- A Simple Framework for Contrastive Learning of Visual Representations
- Prototypical Networks for Few-shot Learning
- Learning Transferable Features with Deep Adaptation Networks
- Deep Visual Domain Adaptation: A Survey
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Conditional Adversarial Domain Adaptation
- Semantic Foggy Scene Understanding with Synthetic Data
- Momentum Contrast for Unsupervised Visual Representation Learning
- Continual Learning Through Synaptic Intelligence
- Zero-Shot Learning Through Cross-Modal Transfer
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- A review of domain adaptation without target labels
- Domain Separation Networks
- Domain Generalization via Invariant Feature Representation
- VisDA: The Visual Domain Adaptation Challenge
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Domain Adaptation: Learning Bounds and Algorithms
- Beyond Sharing Weights for Deep Domain Adaptation
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- Overcoming Catastrophic Forgetting by Incremental Moment Matching
- Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
- Unsupervised Domain Adaptation through Self-Supervision
- Self-supervised Domain Adaptation for Computer Vision Tasks
- Analyzing Inverse Problems with Invertible Neural Networks
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Domain Agnostic Learning with Disentangled Representations
- Algorithms and Theory for Multiple-Source Adaptation
- Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
- Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
- Multiple Source Adaptation and the Renyi Divergence
- Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
- Private Federated Learning with Domain Adaptation
- Regularized Learning for Domain Adaptation under Label Shifts
- Analysis of Kernel Mean Matching under Covariate Shift
- Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
- Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories
- Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels
- Self-Supervised Learning for Domain Adaptation on Point-Clouds
- Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
- Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
- SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
- Dual Adversarial Domain Adaptation
- On Target Shift in Adversarial Domain Adaptation
- Class-imbalanced Domain Adaptation: An Empirical Odyssey
- Generalized Zero-shot ICD Coding