Segment Any Change
Keywords: change detection, remote sensing, zero-shot adaptation, visual foundation models, satellite imagery
TL;DR: Our training-free adaptation enables Segment Anything Model (SAM) to zero-shot change detection by exploiting the latent space of SAM
Abstract: Visual foundation models have achieved remarkable results in zero-shot image classification and segmentation, but zero-shot change detection remains an open problem.
In this paper, we propose the segment any change models (AnyChange), a new type of change detection model that supports zero-shot prediction and generalization on unseen change types and data distributions.
AnyChange is built on the segment anything model (SAM) via our training-free adaptation method, bitemporal latent matching.
By revealing and exploiting intra-image and inter-image semantic similarities in SAM's latent space, bitemporal latent matching endows SAM with zero-shot change detection capabilities in a training-free way.
We also propose a point query mechanism to enable AnyChange's zero-shot object-centric change detection capability.
We perform extensive experiments to confirm the effectiveness of AnyChange for zero-shot change detection.
AnyChange sets a new record on the SECOND benchmark for unsupervised change detection, exceeding the previous SOTA by up to 4.4\% F$_1$ score, and achieving comparable accuracy with negligible manual annotations (1 pixel per image) for supervised change detection. Code is available at https://github.com/Z-Zheng/pytorch-change-models.
Primary Area: Machine vision
Submission Number: 1359
Loading