# Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/1703.01461 · HTML: https://mlsanity.com/paper/1703.01461/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2017.

## Built on by (most cited first, 22 of 22)

- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving](https://mlsanity.com/paper/2202.07133/) (2022)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Deep vanishing point detection: Geometric priors make dataset variations vanish](https://mlsanity.com/paper/2203.08586/) (2022)
- [Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation](https://mlsanity.com/paper/2303.05194/) (2023)
- [Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation](https://mlsanity.com/paper/2402.07127/) (2024)
- [Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation](https://mlsanity.com/paper/2103.14496/) (2021)
- [An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2203.03568/) (2022)
- [Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning](https://mlsanity.com/paper/2309.16074/) (2023)
- [Generalized Label Shift Correction via Minimum Uncertainty Principle: Theory and Algorithm](https://mlsanity.com/paper/2202.13043/) (2022)
- [BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task](https://mlsanity.com/paper/2202.13174/) (2022)
- [A Multi-stage Framework with Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.00003/) (2022)
- [One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers](https://mlsanity.com/paper/2212.07292/) (2022)
- [Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living](https://mlsanity.com/paper/2208.01910/) (2022)
- [Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation](https://mlsanity.com/paper/2310.04747/) (2023)
- [On the Challenges of Open World Recognitionunder Shifting Visual Domains](https://mlsanity.com/paper/2107.04461/) (2021)
- [ADL-ID: Adversarial Disentanglement Learning for Wireless Device Fingerprinting Temporal Domain Adaptation](https://mlsanity.com/paper/2301.12360/) (2023)
- [Cross-modality debiasing: using language to mitigate sub-population shifts in imaging](https://mlsanity.com/paper/2403.07888/) (2024)
- [Generalizing Segmentation Foundation Model Under Sim-to-real Domain-shift for Guidewire Segmentation in X-ray Fluoroscopy](https://mlsanity.com/paper/2410.07460/) (2024)
- [EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems](https://mlsanity.com/paper/2505.00986/) (2025)
- [cGANs for Cartoon to Real-life Images](https://mlsanity.com/paper/2101.09793/) (2021)

## Abstract (arXiv)

Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it will deliver degraded performance in application domains that underlie distributional shifts caused by these changes. Traditionally, this problem has been addressed via the collection of labelled data in multiple domains or by imposing priors on the type of shift between both domains. We frame the problem in the context of unsupervised domain adaptation and develop a framework for applying adversarial techniques to adapt popular, state-of-the-art network architectures with the additional objective to align features across domains. Moreover, as adversarial training is notoriously unstable, we first perform an extensive ablation study, adapting many techniques known to stabilise generative adversarial networks, and evaluate on a surrogate classification task with the same appearance change. The distilled insights are applied to the problem of free-space segmentation for motion planning in autonomous driving.