Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process (2309.17031v1)
Abstract: Understanding the temporal dynamics of Earth's surface is a mission of multi-temporal remote sensing image analysis, significantly promoted by deep vision models with its fuel -- labeled multi-temporal images. However, collecting, preprocessing, and annotating multi-temporal remote sensing images at scale is non-trivial since it is expensive and knowledge-intensive. In this paper, we present a scalable multi-temporal remote sensing change data generator via generative modeling, which is cheap and automatic, alleviating these problems. Our main idea is to simulate a stochastic change process over time. We consider the stochastic change process as a probabilistic semantic state transition, namely generative probabilistic change model (GPCM), which decouples the complex simulation problem into two more trackable sub-problems, \ie, change event simulation and semantic change synthesis. To solve these two problems, we present the change generator (Changen), a GAN-based GPCM, enabling controllable object change data generation, including customizable object property, and change event. The extensive experiments suggest that our Changen has superior generation capability, and the change detectors with Changen pre-training exhibit excellent transferability to real-world change datasets.
- Wele Gedara Chaminda Bandara and Vishal M. Patel. A transformer-based siamese network for change detection. In IGARSS, pages 207–210, 2022.
- Constrained optical flow for aerial image change detection. In 2011 IEEE International Geoscience and Remote Sensing Symposium, pages 4176–4179. IEEE, 2011.
- Signature verification using a” siamese” time delay neural network. In NeurIPS, 1994.
- Adversarial instance augmentation for building change detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 60:1–16, 2021.
- Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing, 60:1–14, 2021.
- A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing, 12(10):1662, 2020.
- Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297, 2020.
- Fully convolutional siamese networks for change detection. In ICIP, pages 4063–4067. IEEE, 2018.
- ImageNet: A large-scale hierarchical image database. In CVPR, pages 248–255, 2009.
- Generating images with perceptual similarity metrics based on deep networks. In NeurIPS, volume 29, 2016.
- Sentinel-2: Esa’s optical high-resolution mission for gmes operational services. Remote sensing of Environment, 120:25–36, 2012.
- Simple copy-paste is a strong data augmentation method for instance segmentation. In CVPR, pages 2918–2928, 2021.
- xbd: A dataset for assessing building damage from satellite imagery. arXiv preprint arXiv:1911.09296, 2019.
- A survey on vision transformer. IEEE TPAMI, 2022.
- Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
- Gans trained by a two time-scale update rule converge to a local nash equilibrium. In NeurIPS, volume 30, 2017.
- Image-to-image translation with conditional adversarial networks. In CVPR, pages 1125–1134, 2017.
- Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing, 57(1):574–586, 2018.
- Perceptual losses for real-time style transfer and super-resolution. In ECCV, pages 694–711. Springer, 2016.
- Adam: A method for stochastic optimization. In ICLR, 2014.
- Procedural synthesis of remote sensing images for robust change detection with neural networks. In International Symposium on Neural Networks, pages 371–387. Springer, 2019.
- Seasonal contrast: Unsupervised pre-training from uncurated remote sensing data. In ICCV, pages 9414–9423, 2021.
- Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
- Spectral normalization for generative adversarial networks. In ICLR, 2018.
- Semantic image synthesis with spatially-adaptive normalization. In CVPR, pages 2337–2346, 2019.
- U-net: Convolutional networks for biomedical image segmentation. In MICCAI, pages 234–241. Springer, 2015.
- Improved techniques for training gans. In NeurIPS, volume 29, 2016.
- You only need adversarial supervision for semantic image synthesis. In ICLR, 2021.
- S2looking: A satellite side-looking dataset for building change detection. Remote Sensing, 13(24):5094, 2021.
- Retrieval-based spatially adaptive normalization for semantic image synthesis. In CVPR, pages 11224–11233, 2022.
- Diverse semantic image synthesis via probability distribution modeling. In CVPR, pages 7962–7971, 2021.
- Alexandru Telea. An image inpainting technique based on the fast marching method. Journal of graphics tools, 9(1):23–34, 2004.
- Large-scale deep learning based binary and semantic change detection in ultra high resolution remote sensing imagery: From benchmark datasets to urban application. ISPRS Journal of Photogrammetry and Remote Sensing, 193:164–186, 2022.
- DynamicEarthNet: Daily multi-spectral satellite dataset for semantic change segmentation. In CVPR, pages 21158–21167, 2022.
- Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022, 2016.
- An empirical study of remote sensing pretraining. IEEE Transactions on Geoscience and Remote Sensing, 2022.
- High-resolution image synthesis and semantic manipulation with conditional gans. In CVPR, pages 8798–8807, 2018.
- Group normalization. In ECCV, pages 3–19, 2018.
- SegFormer: Simple and efficient design for semantic segmentation with transformers. In NeurIPS, volume 34, pages 12077–12090, 2021.
- Free-form image inpainting with gated convolution. In ICCV, pages 4471–4480, 2019.
- Change is Everywhere: Single-temporal supervised object change detection in remote sensing imagery. In ICCV, pages 15193–15202, 2021.
- ChangeMask: Deep multi-task encoder-transformer-decoder architecture for semantic change detection. ISPRS Journal of Photogrammetry and Remote Sensing, 183:228–239, 2022.
- Foreground-aware relation network for geospatial object segmentation in high spatial resolution remote sensing imagery. In CVPR, pages 4096–4105, 2020.
- Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: From natural disasters to man-made disasters. Remote Sensing of Environment, 265:112636, 2021.
- FarSeg++: Foreground-aware relation network for geospatial object segmentation in high spatial resolution remote sensing imagery. IEEE TPAMI, 2023.
- Semantic understanding of scenes through the ade20k dataset. IJCV, 127(3):302–321, 2019.
- SEAN: Image synthesis with semantic region-adaptive normalization. In CVPR, pages 5104–5113, 2020.