UniChange: Unifying Change Detection with Multimodal Large Language Model

TL;DR

UniChange leverages multimodal large language models to unify binary and semantic change detection tasks, enabling knowledge transfer across datasets and achieving state-of-the-art results on multiple benchmarks.

Contribution

This work introduces UniChange, the first MLLM-based unified change detection model that integrates generative language abilities with change detection functionalities using special tokens and text prompts.

Findings

Achieves state-of-the-art IoU scores on four public benchmarks.

Effectively unifies BCD and SCD tasks through special tokens.

Demonstrates strong generalization across diverse datasets.

Abstract

Change detection (CD) is a fundamental task for monitoring and analyzing land cover dynamics. While recent high performance models and high quality datasets have significantly advanced the field, a critical limitation persists. Current models typically acquire limited knowledge from single-type annotated data and cannot concurrently leverage diverse binary change detection (BCD) and semantic change detection (SCD) datasets. This constraint leads to poor generalization and limited versatility. The recent advancements in Multimodal Large Language Models (MLLMs) introduce new possibilities for a unified CD framework. We leverage the language priors and unification capabilities of MLLMs to develop UniChange, the first MLLM-based unified change detection model. UniChange integrates generative language abilities with specialized CD functionalities. Our model successfully unifies both BCD and SCD tasks through the introduction of three special tokens: [T1], [T2], and [CHANGE]. Furthermore, UniChange utilizes text prompts to guide the identification of change categories, eliminating the reliance on predefined classification heads. This design allows UniChange to effectively acquire knowledge from multi-source datasets, even when their class definitions conflict. Experiments on four public benchmarks (WHU-CD, S2Looking, LEVIR-CD+, and SECOND) demonstrate SOTA performance, achieving IoU scores of 90.41, 53.04, 78.87, and 57.62, respectively, surpassing all previous methods. The code is available at https://github.com/Erxucomeon/UniChange.