Can I read Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model on EtoBox?

Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model by Zheng, Zhuo; Ermon, Stefano; Kim, Dongjun; Zhang, Liangpei; Zhong, Yanfei is a scholarly article available to read on EtoBox.

What is Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model about?

Our understanding of the temporal dynamics of the Earth's surface has been advanced by deep vision models, which often require lots 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 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 (GPCM), which factorizes the complex simulation problem into two more tractable sub-problems, i.e., change event simulation and semantic change synthesis. To solve these two problems, we present Changen2, a GPCM with a resolution-scalable diffusion transformer which can generate time series of images and their semantic and change labels from labeled or unlabeled single-temporal images. Changen2 is a generative change foundation model that can be trained at scale via self-supervision, and can produce change supervisory signals from unlabeled single-temporal images. Unlik

Author

Zheng, Zhuo; Ermon, Stefano; Kim, Dongjun; Zhang, Liangpei; Zhong, Yanfei

Published

2024

Language

EN