mlsanityData to 14 Oct 2026

MS-Former: Memory-Supported Transformer for Weakly Supervised Change Detection with Patch-Level Annotations

arXiv 2311.09726 ↗First posted 16 Nov 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Fully supervised change detection methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information corresponding to both changed and unchanged objects in bi-temporal images, an intuitive solution is to segment the changes with patch-level annotations. How to capture the semantic variations associated with the changed and unchanged regions from the patch-level annotations to obtain promising change results is the critical challenge for the weakly supervised change detection task. In this paper, we propose a memory-supported transformer (MS-Former), a novel framework consisting of a bi-directional attention block (BAB) and a patch-level supervision scheme (PSS) tailored for weakly supervised change detection with patch-level annotations. More specifically, the BAM captures contexts associated with the changed and unchanged regions from the temporal difference features to construct informative prototypes stored in the memory bank. On the other hand, the BAM extracts useful information from the prototypes as supplementary contexts to enhance the temporal difference features, thereby better distinguishing changed and unchanged regions. After that, the PSS guides the network learning valuable knowledge from the patch-level annotations, thus further elevating the performance. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method in the change detection task. The demo code for our work will be publicly available at urlhttps://github.com/guanyuezhen/MS-Former.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 63 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

32 of 63 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2023Segment Anythingcited by 8,234
  7. 2017Squeeze-and-Excitation Networkscited by 4,789
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  9. 2017Non-local Neural Networkscited by 2,293
  10. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  11. 2019Panoptic Feature Pyramid Networkscited by 645
  12. 2018Fully Convolutional Siamese Networks for Change Detectioncited by 306
20 more
  1. 2021Remote Sensing Image Change Detection with Transformerscited by 306
  2. 2021Concealed Object Detectioncited by 212
  3. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  4. 2021Efficient Regional Memory Network for Video Object Segmentationcited by 86
  5. 2021P2T: Pyramid Pooling Transformer for Scene Understandingcited by 84
  6. 2022Changer: Feature Interaction is What You Need for Change Detectioncited by 79
  7. 2021Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagerycited by 64
  8. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  9. 2022Fully Convolutional Change Detection Framework with Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detectioncited by 46
  10. 2022Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detectioncited by 26
  11. 2023Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrievalcited by 23
  12. 2022Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Poolingcited by 19
  13. 2023Salient Object Detection in Optical Remote Sensing Images Driven by Transformercited by 17
  14. 2023Detecting Building Changes with Off-Nadir Aerial Imagescited by 16
  15. 2023Adjacent-Level Feature Cross-Fusion With 3-D CNN for Remote Sensing Image Change Detectioncited by 13
  16. 2023TransY-Net:Learning Fully Transformer Networks for Change Detection of Remote Sensing Imagescited by 13
  17. 2020A Weakly Supervised Convolutional Network for Change Segmentation and Classificationcited by 11
  18. 2022Background-Mixed Augmentation for Weakly Supervised Change Detectioncited by 11
  19. 2023Exploring Effective Priors and Efficient Models for Weakly-Supervised Change Detectioncited by 5
  20. 2023Hard Region Aware Network for Remote Sensing Change Detectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2024A Change Detection Reality Checkcited by 13
  2. 2025Advancing Weakly-Supervised Change Detection in Satellite Images via Adversarial Class Promptingcited by 3
  3. 2024AdaSemiCD: An Adaptive Semi-Supervised Change Detection Method Based on Pseudo-Label Evaluationcited by 2
  4. 2026OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagerycited by 2
  5. 2025Plug-and-Play DISep: Separating Dense Instances for Scene-to-Pixel Weakly-Supervised Change Detection in High-Resolution Remote Sensing Imagescited by 0
  6. 2026Progressive Pseudo-Label Optimization for Point-Supervised Change Detectioncited by 0