# Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

arXiv: https://arxiv.org/abs/2003.04382 · HTML: https://mlsanity.com/paper/2003.04382/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2020.

## Built on by (most cited first, 19 of 19)

- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.10856/) (2022)
- [Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time](https://mlsanity.com/paper/2108.06721/) (2021)
- [BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning](https://mlsanity.com/paper/2305.04769/) (2023)
- [Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder](https://mlsanity.com/paper/2205.07649/) (2022)
- [Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions](https://mlsanity.com/paper/2207.10667/) (2022)
- [To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2307.15063/) (2023)
- [Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition](https://mlsanity.com/paper/2106.03351/) (2021)
- [Task-agnostic Continual Hippocampus Segmentation for Smooth Population Shifts](https://mlsanity.com/paper/2208.03206/) (2022)
- [Delving into the Continuous Domain Adaptation](https://mlsanity.com/paper/2208.13121/) (2022)
- [Enhancing Evolving Domain Generalization through Dynamic Latent Representations](https://mlsanity.com/paper/2401.08464/) (2024)
- [Towards Unified and Effective Domain Generalization](https://mlsanity.com/paper/2310.10008/) (2023)
- [Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics](https://mlsanity.com/paper/2111.13069/) (2021)
- [Class incremental learning with probability dampening and cascaded gated classifier](https://mlsanity.com/paper/2402.01262/) (2024)
- [Gradient Regularized Contrastive Learning for Continual Domain Adaptation](https://mlsanity.com/paper/2103.12294/) (2021)
- [KRNet: Towards Efficient Knowledge Replay](https://mlsanity.com/paper/2205.11126/) (2022)
- [Prompting-based Temporal Domain Generalization](https://mlsanity.com/paper/2310.02473/) (2023)

## Abstract (arXiv)

Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This paper aims to tackle this challenge in the context of continuous domain adaptation, where the model is required to learn new tasks adapted to new domains in a non-stationary environment while maintaining previously learned knowledge. To deal with both drifts, we propose variational domain-agnostic feature replay, an approach that is composed of three components: an inference module that filters the input data into domain-agnostic representations, a generative module that facilitates knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We address the two fundamental scenarios in continuous domain adaptation, demonstrating the effectiveness of our proposed approach for practical usage.