Segment Any Change
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 (1)
Tasks
Change Detectionimage-classificationImage ClassificationZero-Shot Image ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
How to Reduce Change Detection to Semantic Segmentation
Change detection (CD) aims to identify changes that occur in an image pair taken different times. Prior methods devise specific networks from scratch to predict change masks in pixel-level, and struggle with general segm…
Change DetectionScene Change DetectionSegmentationSemantic SegmentationCCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation
Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing. However, traditional Image Change Captioning (ICC) methods lack spatial grounding, limiting …
Change DetectionImage EditingA Weakly Supervised Convolutional Network for Change Segmentation and Classification
Fully supervised change detection methods require difficult to procure pixel-level labels, while weakly supervised approaches can be trained with image-level labels. However, most of these approaches require a combinatio…
Change DetectionClassificationGeneral ClassificationLand Cover Change Detection via Semantic Segmentation
This paper presents a change detection method that identifies land cover changes from aerial imagery, using semantic segmentation, a machine learning approach. We present a land cover classification training pipeline wit…
Change DetectionGeneral ClassificationLand Cover ClassificationManagement+2Segment Parameter Labelling in MCMC Mean-Shift Change Detection
This work addresses the problem of segmentation in time series data with respect to a statistical parameter of interest in Bayesian models. It is common to assume that the parameters are distinct within each segment. As …
Change DetectionChange Point DetectionTime SeriesTime Series Analysis