# ACE: Adapting to Changing Environments for Semantic Segmentation

arXiv: https://arxiv.org/abs/1904.06268 · HTML: https://mlsanity.com/paper/1904.06268/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2019.

## Built on by (most cited first, 30 of 44)

- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation](https://mlsanity.com/paper/2211.07609/) (2022)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Multi-Domain Incremental Learning for Semantic Segmentation](https://mlsanity.com/paper/2110.12205/) (2021)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (2022)
- [Unsupervised Continual Semantic Adaptation through Neural Rendering](https://mlsanity.com/paper/2211.13969/) (2022)
- [Domain-Specific Bias Filtering for Single Labeled Domain Generalization](https://mlsanity.com/paper/2110.00726/) (2021)
- [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)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [Zero-Shot Scene Change Detection](https://mlsanity.com/paper/2406.11210/) (2024)
- [Introducing Intermediate Domains for Effective Self-Training during Test-Time](https://mlsanity.com/paper/2208.07736/) (2022)
- [A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework](https://mlsanity.com/paper/2108.07979/) (2021)
- [Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition](https://mlsanity.com/paper/2106.03351/) (2021)
- [Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation](https://mlsanity.com/paper/2311.12682/) (2023)
- [Online Continual Adaptation with Active Self-Training](https://mlsanity.com/paper/2106.06526/) (2021)
- [Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer](https://mlsanity.com/paper/2208.06507/) (2022)
- [Generative appearance replay for continual unsupervised domain adaptation](https://mlsanity.com/paper/2301.01211/) (2023)
- [Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation](https://mlsanity.com/paper/2306.02314/) (2023)
- [Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2309.14241/) (2023)
- [Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2503.21780/) (2025)
- [Multi-level Domain Adaptation for Lane Detection](https://mlsanity.com/paper/2206.10692/) (2022)

## Abstract (arXiv)

Deep neural networks exhibit exceptional accuracy when they are trained and tested on the same data distributions. However, neural classifiers are often extremely brittle when confronted with domain shift---changes in the input distribution that occur over time. We present ACE, a framework for semantic segmentation that dynamically adapts to changing environments over the time. By aligning the distribution of labeled training data from the original source domain with the distribution of incoming data in a shifted domain, ACE synthesizes labeled training data for environments as it sees them. This stylized data is then used to update a segmentation model so that it performs well in new environments. To avoid forgetting knowledge from past environments, we introduce a memory that stores feature statistics from previously seen domains. These statistics can be used to replay images in any of the previously observed domains, thus preventing catastrophic forgetting. In addition to standard batch training using stochastic gradient decent (SGD), we also experiment with fast adaptation methods based on adaptive meta-learning. Extensive experiments are conducted on two datasets from SYNTHIA, the results demonstrate the effectiveness of the proposed approach when adapting to a number of tasks.