Domain Impression: A Source Data Free Domain Adaptation Method
arXiv:2102.09003
Abstract
Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availability of actual source samples is not always possible in practical cases. It could be due to memory constraints, privacy concerns, and challenges in sharing data. This practical scenario creates a bottleneck in the domain adaptation problem. This paper addresses this challenging scenario by proposing a domain adaptation technique that does not need any source data. Instead of the source data, we are only provided with a classifier that is trained on the source data. Our proposed approach is based on a generative framework, where the trained classifier is used for generating samples from the source classes. We learn the joint distribution of data by using the energy-based modeling of the trained classifier. At the same time, a new classifier is also adapted for the target domain. We perform various ablation analysis under different experimental setups and demonstrate that the proposed approach achieves better results than the baseline models in this extremely novel scenario.
arXiv commentPublished- WACV-2021
References in corpus (9)
- Conditional Generative Adversarial Nets
- Deep Learning with Differential Privacy
- Deep Domain Confusion: Maximizing for Domain Invariance
- Conditional Adversarial Domain Adaptation
- Model Adaptation: Unsupervised Domain Adaptation without Source Data
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
- Zero-Shot Knowledge Distillation in Deep Networks