# Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning

arXiv: https://arxiv.org/abs/2012.04324 · HTML: https://mlsanity.com/paper/2012.04324/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 30 of 55)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Conditional Image-to-Video Generation with Latent Flow Diffusion Models](https://mlsanity.com/paper/2303.13744/) (2023)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Synthetic Datasets for Autonomous Driving: A Survey](https://mlsanity.com/paper/2304.12205/) (2023)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [Collaborating Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.09788/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [General Incremental Learning with Domain-aware Categorical Representations](https://mlsanity.com/paper/2204.04078/) (2022)
- [On Generalizing Beyond Domains in Cross-Domain Continual Learning](https://mlsanity.com/paper/2203.03970/) (2022)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (2022)
- [InCloud: Incremental Learning for Point Cloud Place Recognition](https://mlsanity.com/paper/2203.00807/) (2022)
- [Does Continual Learning Equally Forget All Parameters?](https://mlsanity.com/paper/2304.04158/) (2023)
- [Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-world](https://mlsanity.com/paper/2212.00972/) (2022)
- [Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting](https://mlsanity.com/paper/2404.17245/) (2024)
- [Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments](https://mlsanity.com/paper/2305.15700/) (2023)
- [Label-Efficient Domain Generalization via Collaborative Exploration and Generalization](https://mlsanity.com/paper/2208.03644/) (2022)
- [FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding](https://mlsanity.com/paper/2311.15965/) (2023)
- [Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2204.11667/) (2022)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars](https://mlsanity.com/paper/2212.00621/) (2022)
- [Cloud-Device Collaborative Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2312.16279/) (2023)
- [Learning with Style: Continual Semantic Segmentation Across Tasks and Domains](https://mlsanity.com/paper/2210.07016/) (2022)
- [Exploring Compositional Visual Generation with Latent Classifier Guidance](https://mlsanity.com/paper/2304.12536/) (2023)
- [Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning](https://mlsanity.com/paper/2409.10956/) (2024)
- [Assessor-Guided Learning for Continual Environments](https://mlsanity.com/paper/2303.11624/) (2023)
- [Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously](https://mlsanity.com/paper/2311.13816/) (2023)

## Abstract (arXiv)

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns from different visual domains, it tends to forget the past domains in favor of the most recent ones. In this context, we show that one way to learn models that are inherently more robust against forgetting is domain randomization - for vision tasks, randomizing the current domain's distribution with heavy image manipulations. Building on this result, we devise a meta-learning strategy where a regularizer explicitly penalizes any loss associated with transferring the model from the current domain to different "auxiliary" meta-domains, while also easing adaptation to them. Such meta-domains are also generated through randomized image manipulations. We empirically demonstrate in a variety of experiments - spanning from classification to semantic segmentation - that our approach results in models that are less prone to catastrophic forgetting when transferred to new domains.