# SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning

arXiv: https://arxiv.org/abs/2006.10386 · HTML: https://mlsanity.com/paper/2006.10386/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [Rethinking Precision of Pseudo Label: Test-Time Adaptation via Complementary Learning](https://mlsanity.com/paper/2301.06013/) (2023)
- [Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective](https://mlsanity.com/paper/2305.15699/) (2023)
- [Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation](https://mlsanity.com/paper/2204.02111/) (2022)
- [EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding](https://mlsanity.com/paper/2406.01429/) (2024)
- [When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather](https://mlsanity.com/paper/2403.13762/) (2024)
- [CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation](https://mlsanity.com/paper/2304.07199/) (2023)
- [ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2107.14285/) (2021)
- [E-CHUM: Event-based Cameras for Human Detection and Urban Monitoring](https://mlsanity.com/paper/2512.11076/) (2025)
- [Rethinking Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2207.00067/) (2022)

## Abstract (arXiv)

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data in order to adapt them to the new domain using fine-tuning. This process is required whenever an already installed camera is moved or a new camera is introduced in a camera network due to the different scene layouts induced by the different viewpoints. To limit the amount of additional training data to be collected, it would be ideal to train a semantic segmentation method using labeled data already available and only unlabeled data coming from the new camera. We formalize this problem as a domain adaptation task and introduce a novel dataset of urban scenes with the related semantic labels. As a first approach to address this challenging task, we propose SceneAdapt, a method for scene adaptation of semantic segmentation algorithms based on adversarial learning. Experiments and comparisons with state-of-the-art approaches to domain adaptation highlight that promising performance can be achieved using adversarial learning both when the two scenes have different but points of view, and when they comprise images of completely different scenes. To encourage research on this topic, we made our code available at our web page: https://iplab.dmi.unict.it/ParkSmartSceneAdaptation/.