# Unsupervised Change Detection Based on Image Reconstruction Loss

arXiv: https://arxiv.org/abs/2204.01200 · HTML: https://mlsanity.com/paper/2204.01200/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images](https://mlsanity.com/paper/1905.12886/) (2019)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2011.09766/) (2020)
- [Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2108.07002/) (2021)
- [Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2011.03247/) (2020)
- [A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset](https://mlsanity.com/paper/2003.00637/) (2020)
- [Unsupervised Change Detection in Satellite Images with Generative Adversarial Network](https://mlsanity.com/paper/2009.03630/) (2020)
- [Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks](https://mlsanity.com/paper/1812.05815/) (2018)

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

- [Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2212.10236/) (2022)
- [Towards Generalizable Scene Change Detection](https://mlsanity.com/paper/2409.06214/) (2024)
- [MapFormer: Boosting Change Detection by Using Pre-change Information](https://mlsanity.com/paper/2303.17859/) (2023)
- [VcT: Visual change Transformer for Remote Sensing Image Change Detection](https://mlsanity.com/paper/2310.11417/) (2023)
- [A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges](https://mlsanity.com/paper/2502.02835/) (2025)
- [Unsupervised Flood Detection on SAR Time Series](https://mlsanity.com/paper/2212.03675/) (2022)
- [SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptation](https://mlsanity.com/paper/2405.18224/) (2024)
- [Improved Flood Insights: Diffusion-Based SAR to EO Image Translation](https://mlsanity.com/paper/2307.07123/) (2023)
- [UCDFormer: Unsupervised Change Detection Using a Transformer-driven Image Translation](https://mlsanity.com/paper/2308.01146/) (2023)
- [CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.11606/) (2023)
- [S2C: Learning Noise-Resistant Differences for Unsupervised Change Detection in Multimodal Remote Sensing Images](https://mlsanity.com/paper/2502.12604/) (2025)
- [SoftMatch Distance: A Novel Distance for Weakly-Supervised Trend Change Detection in Bi-Temporal Images](https://mlsanity.com/paper/2303.04737/) (2023)
- [Reducing False Alarms in Video Surveillance by Deep Feature Statistical Modeling](https://mlsanity.com/paper/2307.04159/) (2023)
- [SCL: Towards Domain Generalization via Single-Temporal Multimodal Contrastive Learning for Remote Sensing Change Detection](https://mlsanity.com/paper/2404.11326/) (2024)
- [Remote Sensing Change Detection via Weak Temporal Supervision](https://mlsanity.com/paper/2601.02126/) (2026)
- [Revisiting Change Detection Methods for their Application to Serac Fall Time-Lapse Monitoring](https://mlsanity.com/paper/2605.28100/) (2026)
- [1st Place Solution to MultiEarth 2023 Challenge on Multimodal SAR-to-EO Image Translation](https://mlsanity.com/paper/2306.12626/) (2023)
- [Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection](https://mlsanity.com/paper/2601.17747/) (2026)
- [Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations](https://mlsanity.com/paper/2602.19881/) (2026)
- [Spatially Selective Self-Training for Unsupervised Building Change Detection](https://mlsanity.com/paper/2606.10775/) (2026)
- [Zero-OVCD: Bridging Training-Free Foundation Models and Pseudo-Label Learning for Open-Vocabulary Change Detection](https://mlsanity.com/paper/2608.11663/) (2026)
- [Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes](https://mlsanity.com/paper/2609.10356/) (2026)

## Abstract (arXiv)

To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming. To solve this problem, various unsupervised change detection methods have been proposed, but they still require unlabeled bi-temporal images. In this paper, we propose unsupervised change detection based on image reconstruction loss using only unlabeled single temporal single image. The image reconstruction model is trained to reconstruct the original source image by receiving the source image and the photometrically transformed source image as a pair. During inference, the model receives bi-temporal images as the input, and tries to reconstruct one of the inputs. The changed region between bi-temporal images shows high reconstruction loss. Our change detector showed significant performance in various change detection benchmark datasets even though only a single temporal single source image was used. The code and trained models will be publicly available for reproducibility.