mlsanityData to 7 Oct 2026

Supervising Remote Sensing Change Detection Models with 3D Surface Semantics

arXiv 2202.13251 ↗First posted 26 Feb 2022cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Remote sensing change detection, identifying changes between scenes of the same location, is an active area of research with a broad range of applications. Recent advances in multimodal self-supervised pretraining have resulted in state-of-the-art methods which surpass vision models trained solely on optical imagery. In the remote sensing field, there is a wealth of overlapping 2D and 3D modalities which can be exploited to supervise representation learning in vision models. In this paper we propose Contrastive Surface-Image Pretraining (CSIP) for joint learning using optical RGB and above ground level (AGL) map pairs. We then evaluate these pretrained models on several building segmentation and change detection datasets to show that our method does, in fact, extract features relevant to downstream applications where natural and artificial surface information is relevant.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 26 Feb 2022.

Builds on

18 of 25 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2021Vision Transformers for Dense Predictioncited by 1,789
  7. 2018Fully Convolutional Siamese Networks for Change Detectioncited by 305
  8. 2021Remote Sensing Image Change Detection with Transformerscited by 305
  9. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 214
  10. 2019xBD: A Dataset for Assessing Building Damage from Satellite Imagerycited by 138
  11. 2018Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networkscited by 108
  12. 2021S2Looking: A Satellite Side-Looking Dataset for Building Change Detectioncited by 77
6 more
  1. 2021TorchGeo: Deep Learning With Geospatial Datacited by 73
  2. 2020LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagerycited by 40
  3. 2021Self-supervised Audiovisual Representation Learning for Remote Sensing Datacited by 24
  4. 2021Self-supervised pre-training enhances change detection in Sentinel-2 imagerycited by 21
  5. 2020Learning Geocentric Object Pose in Oblique Monocular Imagescited by 16
  6. 2021Self-supervised Remote Sensing Images Change Detection at Pixel-levelcited by 9

Built on by

Cited by year

Citing papers per year: 2023: 4.

4 papers.

  1. 2023CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoderscited by 167
  2. 2023Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matterscited by 27
  3. 2023Single-View Height Estimation with Conditional Diffusion Probabilistic Modelscited by 1
  4. 2023ZRG: A Dataset for Multimodal 3D Residential Rooftop Understandingcited by 0