mlsanityData to 7 Oct 2026

ChangeViT: Unleashing Plain Vision Transformers for Change Detection

arXiv 2406.12847 ↗First posted 18 Jun 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Change detection in remote sensing images is essential for tracking environmental changes on the Earth's surface. Despite the success of vision transformers (ViTs) as backbones in numerous computer vision applications, they remain underutilized in change detection, where convolutional neural networks (CNNs) continue to dominate due to their powerful feature extraction capabilities. In this paper, our study uncovers ViTs' unique advantage in discerning large-scale changes, a capability where CNNs fall short. Capitalizing on this insight, we introduce ChangeViT, a framework that adopts a plain ViT backbone to enhance the performance of large-scale changes. This framework is supplemented by a detail-capture module that generates detailed spatial features and a feature injector that efficiently integrates fine-grained spatial information into high-level semantic learning. The feature integration ensures that ChangeViT excels in both detecting large-scale changes and capturing fine-grained details, providing comprehensive change detection across diverse scales. Without bells and whistles, ChangeViT achieves state-of-the-art performance on three popular high-resolution datasets (i.e., LEVIR-CD, WHU-CD, and CLCD) and one low-resolution dataset (i.e., OSCD), which underscores the unleashed potential of plain ViTs for change detection. Furthermore, thorough quantitative and qualitative analyses validate the efficacy of the introduced modules, solidifying the effectiveness of our approach. The source code is available at https://github.com/zhuduowang/ChangeViT.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

34 of 55 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  12. 2017Squeeze-and-Excitation Networkscited by 4,763
22 more
  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  2. 2017Non-local Neural Networkscited by 2,290
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  6. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  7. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  8. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  9. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  10. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  11. 2018Fully Convolutional Siamese Networks for Change Detectioncited by 305
  12. 2021Remote Sensing Image Change Detection with Transformerscited by 305
  13. 2022A Transformer-Based Siamese Network for Change Detectioncited by 243
  14. 2022SimpleClick: Interactive Image Segmentation with Simple Vision Transformerscited by 109
  15. 2018Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networkscited by 108
  16. 2019Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Modelcited by 84
  17. 2022Changer: Feature Interaction is What You Need for Change Detectioncited by 78
  18. 2021Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagerycited by 64
  19. 2023ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformerscited by 56
  20. 2022GhostNetV2: Enhance Cheap Operation with Long-Range Attentioncited by 44
  21. 2023VcT: Visual change Transformer for Remote Sensing Image Change Detectioncited by 11
  22. 2023Adapting Vision Transformer for Efficient Change Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 20253D-SSM: A Novel 3D Selective Scan Module for Remote Sensing Change Detectioncited by 2
  2. 2025Operational Change Detection for Geographical Information: Overview and Challengescited by 0
  3. 2025Flow-CDNet: A Novel Network for Detecting Both Slow and Fast Changes in Bitemporal Imagescited by 0
  4. 2025Multi-Receptive Field Ensemble with Cross-Entropy Masking for Class Imbalance in Remote Sensing Change Detectioncited by 0
  5. 2025Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architecturescited by 0
  6. 2026HA2F: Dual-module Collaboration-Guided Hierarchical Adaptive Aggregation Framework for Remote Sensing Change Detectioncited by 0