mlsanityData to 7 Oct 2026

Unsupervised Change Detection Based on Image Reconstruction Loss

arXiv 2204.01200 ↗First posted 4 Apr 2022cs.CV eess.IVcited by 22

Not on the map. Why?

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

16 of 34 references.

References · 16

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  3. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  4. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  5. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2021Remote Sensing Image Change Detection with Transformerscited by 305
  8. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  9. 2019iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Imagescited by 195
  10. 2018Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networkscited by 108
  11. 2020Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagerycited by 73
  12. 2021Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagerycited by 64
4 more
  1. 2020Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagerycited by 33
  2. 2020A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Datasetcited by 28
  3. 2020Unsupervised Change Detection in Satellite Images with Generative Adversarial Networkcited by 13
  4. 2018Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networkscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 3; 2025: 2; 2026: 7.

22 papers.

Sort:

  1. 2022Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagerycited by 19
  2. 2024Towards Generalizable Scene Change Detectioncited by 17
  3. 2023MapFormer: Boosting Change Detection by Using Pre-change Informationcited by 12
  4. 2023VcT: Visual change Transformer for Remote Sensing Image Change Detectioncited by 11
  5. 2025A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challengescited by 9
  6. 2022Unsupervised Flood Detection on SAR Time Seriescited by 6
  7. 2024SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptationcited by 6
  8. 2023Improved Flood Insights: Diffusion-Based SAR to EO Image Translationcited by 5
  9. 2023UCDFormer: Unsupervised Change Detection Using a Transformer-driven Image Translationcited by 5
  10. 2023CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentationcited by 4
  11. 2025S2C: Learning Noise-Resistant Differences for Unsupervised Change Detection in Multimodal Remote Sensing Imagescited by 2
  12. 2023SoftMatch Distance: A Novel Distance for Weakly-Supervised Trend Change Detection in Bi-Temporal Imagescited by 1
10 more
  1. 2023Reducing False Alarms in Video Surveillance by Deep Feature Statistical Modelingcited by 1
  2. 2024SCL: Towards Domain Generalization via Single-Temporal Multimodal Contrastive Learning for Remote Sensing Change Detectioncited by 1
  3. 2026Remote Sensing Change Detection via Weak Temporal Supervisioncited by 1
  4. 2026Revisiting Change Detection Methods for their Application to Serac Fall Time-Lapse Monitoringcited by 1
  5. 20231st Place Solution to MultiEarth 2023 Challenge on Multimodal SAR-to-EO Image Translationcited by 0
  6. 2026Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detectioncited by 0
  7. 2026Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbationscited by 0
  8. 2026Spatially Selective Self-Training for Unsupervised Building Change Detectioncited by 0
  9. 2026Zero-OVCD: Bridging Training-Free Foundation Models and Pseudo-Label Learning for Open-Vocabulary Change Detectioncited by 0
  10. 2026Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changescited by 0