# Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation

arXiv: https://arxiv.org/abs/1907.11004 · HTML: https://mlsanity.com/paper/1907.11004/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2019.

## Built on by (most cited first, 10 of 10)

- [Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions](https://mlsanity.com/paper/2207.06825/) (2022)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (2022)
- [ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception](https://mlsanity.com/paper/2104.13395/) (2021)
- [Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.04446/) (2022)
- [Improving Road Segmentation in Challenging Domains Using Similar Place Priors](https://mlsanity.com/paper/2205.14112/) (2022)
- [MMS-VPR: A Fine-Grained Multimodal Street-Level Visual Place Recognition Dataset and Evaluation Benchmark for Dense Pedestrian Environments](https://mlsanity.com/paper/2505.12254/) (2025)
- [Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay](https://mlsanity.com/paper/2402.00580/) (2024)
- [Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency](https://mlsanity.com/paper/2402.09237/) (2024)
- [Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention](https://mlsanity.com/paper/2512.11811/) (2025)

## Abstract (arXiv)

Modern models that perform system-critical tasks such as segmentation and localization exhibit good performance and robustness under ideal conditions (i.e. daytime, overcast) but performance degrades quickly and often catastrophically when input conditions change. In this work, we present a domain adaptation system that uses light-weight input adapters to pre-processes input images, irrespective of their appearance, in a way that makes them compatible with off-the-shelf computer vision tasks that are trained only on inputs with ideal conditions. No fine-tuning is performed on the off-the-shelf models, and the system is capable of incrementally training new input adapters in a self-supervised fashion, using the computer vision tasks as supervisors, when the input domain differs significantly from previously seen domains. We report large improvements in semantic segmentation and topological localization performance on two popular datasets, RobotCar and BDD.