# FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images

arXiv: https://arxiv.org/abs/2201.02588 · HTML: https://mlsanity.com/paper/2201.02588/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 55 references that are in the map.
- First posted on arXiv 7 Jan 2022.

## Builds on (most cited first, 30 of 36)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2003.00867/) (2020)
- [No More Discrimination: Cross City Adaptation of Road Scene Segmenters](https://mlsanity.com/paper/1704.08509/) (2017)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation](https://mlsanity.com/paper/1903.12212/) (2019)
- [Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach](https://mlsanity.com/paper/1908.09547/) (2019)
- [Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding](https://mlsanity.com/paper/1808.01265/) (2018)
- [DADA: Depth-aware Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1904.01886/) (2019)
- [ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes](https://mlsanity.com/paper/1711.11556/) (2017)
- [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018)
- [Fully Convolutional Adaptation Networks for Semantic Segmentation](https://mlsanity.com/paper/1804.08286/) (2018)
- [Boosting Domain Adaptation by Discovering Latent Domains](https://mlsanity.com/paper/1805.01386/) (2018)
- [A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes](https://mlsanity.com/paper/1812.09953/) (2018)
- [Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2007.14449/) (2020)
- [Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding](https://mlsanity.com/paper/1901.01415/) (2019)
- [Unsupervised Single Image Dehazing Using Dark Channel Prior Loss](https://mlsanity.com/paper/1812.07051/) (2018)

## Built on by (most cited first, 7 of 7)

- [CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning](https://mlsanity.com/paper/2403.17369/) (2024)
- [Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning](https://mlsanity.com/paper/2311.04815/) (2023)
- [One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers](https://mlsanity.com/paper/2212.07292/) (2022)
- [From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance](https://mlsanity.com/paper/2510.03906/) (2025)
- [Leveraging Topology for Domain Adaptive Road Segmentation in Satellite and Aerial Imagery](https://mlsanity.com/paper/2309.15625/) (2023)
- [AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images](https://mlsanity.com/paper/2503.03370/) (2025)
- [Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network](https://mlsanity.com/paper/2609.02434/) (2026)

## Abstract (arXiv)

This paper presents FogAdapt, a novel approach for domain adaptation of semantic segmentation for dense foggy scenes. Although significant research has been directed to reduce the domain shift in semantic segmentation, adaptation to scenes with adverse weather conditions remains an open question. Large variations in the visibility of the scene due to weather conditions, such as fog, smog, and haze, exacerbate the domain shift, thus making unsupervised adaptation in such scenarios challenging. We propose a self-entropy and multi-scale information augmented self-supervised domain adaptation method (FogAdapt) to minimize the domain shift in foggy scenes segmentation. Supported by the empirical evidence that an increase in fog density results in high self-entropy for segmentation probabilities, we introduce a self-entropy based loss function to guide the adaptation method. Furthermore, inferences obtained at different image scales are combined and weighted by the uncertainty to generate scale-invariant pseudo-labels for the target domain. These scale-invariant pseudo-labels are robust to visibility and scale variations. We evaluate the proposed model on real clear-weather scenes to real foggy scenes adaptation and synthetic non-foggy images to real foggy scenes adaptation scenarios. Our experiments demonstrate that FogAdapt significantly outperforms the current state-of-the-art in semantic segmentation of foggy images. Specifically, by considering the standard settings compared to state-of-the-art (SOTA) methods, FogAdapt gains 3.8% on Foggy Zurich, 6.0% on Foggy Driving-dense, and 3.6% on Foggy Driving in mIoU when adapted from Cityscapes to Foggy Zurich.