# Appearance Based Deep Domain Adaptation for the Classification of Aerial Images

arXiv: https://arxiv.org/abs/2108.07779 · HTML: https://mlsanity.com/paper/2108.07779/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 17 Aug 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [Deep learning in remote sensing: a review](https://mlsanity.com/paper/1710.03959/) (2017)
- [CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency](https://mlsanity.com/paper/2001.03182/) (2020)
- [All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation](https://mlsanity.com/paper/1903.12212/) (2019)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Fully Convolutional Adaptation Networks for Semantic Segmentation](https://mlsanity.com/paper/1804.08286/) (2018)
- [Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data](https://mlsanity.com/paper/2104.07778/) (2021)
- [Phase Consistent Ecological Domain Adaptation](https://mlsanity.com/paper/2004.04923/) (2020)
- [Associative Domain Adaptation](https://mlsanity.com/paper/1708.00938/) (2017)
- [Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images](https://mlsanity.com/paper/1905.03198/) (2019)
- [ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks](https://mlsanity.com/paper/1907.12859/) (2019)
- [Semantically Adaptive Image-to-image Translation for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2009.01166/) (2020)
- [SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data](https://mlsanity.com/paper/2002.05925/) (2020)

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

- [Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory](https://mlsanity.com/paper/2208.07722/) (2022)
- [Universal Domain Adaptation for Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2301.11387/) (2023)
- [A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extraction](https://mlsanity.com/paper/2208.10004/) (2022)
- [ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentation](https://mlsanity.com/paper/2201.11523/) (2022)
- [Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation](https://mlsanity.com/paper/2208.09823/) (2022)
- [SegForestNet: Spatial-Partitioning-Based Aerial Image Segmentation](https://mlsanity.com/paper/2302.01585/) (2023)
- [DAM-Net: Domain Adaptation Network with Micro-Labeled Fine-Tuning for Change Detection](https://mlsanity.com/paper/2504.13748/) (2025)
- [From Pixels to Images: A Structural Survey of Deep Learning Paradigms in Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2505.15147/) (2025)
- [Domain Adaptation for Big Data in Agricultural Image Analysis: A Comprehensive Review](https://mlsanity.com/paper/2506.05972/) (2025)

## Abstract (arXiv)

This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on the setting in which labelled data are only available in a source domain DS, but not in a target domain DT. Our method is based on adversarial training of an appearance adaptation network (AAN) that transforms images from DS such that they look like images from DT. Together with the original label maps from DS, the transformed images are used to adapt a DNN to DT. We propose a joint training strategy of the AAN and the classifier, which constrains the AAN to transform the images such that they are correctly classified. In this way, objects of a certain class are changed such that they resemble objects of the same class in DT. To further improve the adaptation performance, we propose a new regularization loss for the discriminator network used in domain adversarial training. We also address the problem of finding the optimal values of the trained network parameters, proposing an unsupervised entropy based parameter selection criterion which compensates for the fact that there is no validation set in DT that could be monitored. As a minor contribution, we present a new weighting strategy for the cross-entropy loss, addressing the problem of imbalanced class distributions. Our method is evaluated in 42 adaptation scenarios using datasets from 7 cities, all consisting of high-resolution digital orthophotos and height data. It achieves a positive transfer in all cases, and on average it improves the performance in the target domain by 4.3% in overall accuracy. In adaptation scenarios between datasets from the ISPRS semantic labelling benchmark our method outperforms those from recent publications by 10-20% with respect to the mean intersection over union.