|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM378739883 |
| 003 |
DE-627 |
| 005 |
20241014232253.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
241011s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3475824
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1567.xml
|
| 035 |
|
|
|a (DE-627)NLM378739883
|
| 035 |
|
|
|a (NLM)39388323
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zheng, Zhuo
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Changen2
|b Multi-Temporal Remote Sensing Generative Change Foundation Model
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 14.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status Publisher
|
| 520 |
|
|
|a Our understanding of the temporal dynamics of the Earth's surface has been significantly advanced by deep vision models, which often require a massive amount of labeled multi-temporal images for training. 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 scalable multi-temporal change data generators based on generative models, which are cheap and automatic, alleviating these data problems. Our main idea is to simulate a stochastic change process over time. We describe the stochastic change process as a probabilistic graphical model, namely the generative probabilistic change model (GPCM), which factorizes the complex simulation problem into two more tractable sub-problems, i.e., condition-level change event simulation and image-level semantic change synthesis. To solve these two problems, we present Changen2, a GPCM implemented with a resolution-scalable diffusion transformer which can generate time series of remote sensing images and corresponding semantic and change labels from labeled and even unlabeled single-temporal images. Changen2 is a "generative change foundation model" that can be trained at scale via self-supervision, and is capable of producing change supervisory signals from unlabeled single-temporal images. Unlike existing "foundation models", our generative change foundation model synthesizes change data to train task-specific foundation models for change detection. The resulting model possesses inherent zero-shot change detection capabilities and excellent transferability. Comprehensive experiments suggest Changen2 has superior spatiotemporal scalability in data generation, e.g., Changen2 model trained on 256 2 pixel single-temporal images can yield time series of any length and resolutions of 1,024 2 pixels. Changen2 pre-trained models exhibit superior zero-shot performance (narrowing the performance gap to 3% on LEVIR-CD and approximately 10% on both S2Looking and SECOND, compared to fully supervised counterpart) and transferability across multiple types of change tasks, including ordinary and off-nadir building change, land-use/land-cover change, and disaster assessment. The model and datasets are available at https://github.com/Z-Zheng/pytorch-change-models
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Ermon, Stefano
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Kim, Dongjun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Liangpei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhong, Yanfei
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g PP(2024) vom: 10. Okt.
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:PP
|g year:2024
|g day:10
|g month:10
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3475824
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d PP
|j 2024
|b 10
|c 10
|