# Domain Transformer: Predicting Samples of Unseen, Future Domains

arXiv: https://arxiv.org/abs/2106.06057 · HTML: https://mlsanity.com/paper/2106.06057/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## Builds on (most cited first, 18 of 18)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Generative Moment Matching Networks](https://mlsanity.com/paper/1502.02761/) (2015)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [Adversarial Latent Autoencoders](https://mlsanity.com/paper/2004.04467/) (2020)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data](https://mlsanity.com/paper/2005.10996/) (2020)
- [Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data](https://mlsanity.com/paper/1802.10151/) (2018)
- [Continuously Indexed Domain Adaptation](https://mlsanity.com/paper/2007.01807/) (2020)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer](https://mlsanity.com/paper/2012.12545/) (2020)
- [Explaining Neural Networks by Decoding Layer Activations](https://mlsanity.com/paper/2005.13630/) (2020)
- [The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2007.12568/) (2020)
- [Multi-Domain Translation by Learning Uncoupled Autoencoders](https://mlsanity.com/paper/1902.03515/) (2019)
- [Cross-Domain Adversarial Auto-Encoder](https://mlsanity.com/paper/1804.06078/) (2018)
- [Locality-Promoting Representation Learning](https://mlsanity.com/paper/1905.10661/) (2019)

## Abstract (arXiv)

The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance. Current techniques are not adequate for this problem because they either require detailed knowledge of the transformation or are not suited for anticipating unseen domains but can only adapt to domains, where data samples are available. We seek to predict unseen data (and their labels) allowing us to tackle challenges s a non-constant data distribution in a proactive manner rather than detecting and reacting to already existing changes that might already have led to errors. To this end, we learn a domain transformer in an unsupervised manner that allows generating data of unseen domains. Our approach first matches independently learned latent representations of two given domains obtained from an auto-encoder using a Cycle-GAN. In turn, a transformation of the original samples can be learned that can be applied iteratively to extrapolate to unseen domains. Our evaluation of CNNs on image data confirms the usefulness of the approach. It also achieves very good results on the well-known problem of unsupervised domain adaption, where only labels but no samples have to be predicted. Code is available at https://github.com/JohnTailor/DoTra.