AI Paper Atlas

Research map / Time series / Foundation models for time series

Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model

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

TPAMI 2024 · Time series › Foundation models for time series · approach: Time series foundation models · 80 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Changen with Changen2 diffusion-transformer generatorChangeStar R-18 zero-shot · LEVIR-CD allF1: 62.8 -> 83.7Improved
replace Changen with Changen2 generatorChangeStar R-18 zero-shot · WHU-CD allF1: 26.6 -> 76.3Improved
use pretrained Stable Diffusion ControlNet instead of DiT trained from scratchGPCM generators · xView2 holdFID: 32.33 -> 101.45Hurt
use Changen2 instead of Changen for image qualityChangen · xView2 holdFID: 34.74 -> 32.44Improved
scale change detector backbone from R-18 to ViT-B under zero-shotChangen2 pretraining · LEVIR-CDF1: 83.7 -> 88.7Improved
pretrain on Changen2 synthetic data instead of xView2 segmentation data (ablation)ChangeStar R-18 · LEVIR-CD testF1: 90.6 -> 91.3Improved
pretrain on Changen2 instead of ChangenChangeStar MiT-B1 · LEVIR-CD testF1: 91.5 -> 91.9Improved
pretrain on Changen2 instead of SA-1BChangeStar ViT-B · S2Looking testF1: 68.1 -> 68.5Improved
use smaller pre-event guidance ratio lambda (more temporal diversity) (ablation)Changen2 data · zero-shot LEVIR-CD, S2Looking, othersF1Improved
pretrain on Changen2 instead of OpenEarthMap (ablation)ChangeStar ViT-B · SECOND testSeK37: 21.2 -> 23.0Improved
pretrain on Changen2 instead of OpenEarthMap (ablation)ChangeStar EfficientNet-B0 · SECOND testmIoU30: 27.5 -> 26.2Mixed
zero-shot Changen2 ChangeStar versus AnyChangeChangeStar ViT-B · SECOND BCDF1: 44.6 -> 61.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy