UniChange：以多模态大语言模型统一变化检测
UniChange: Unifying Change Detection with Multimodal Large Language Model
用 MLLM 的语言先验与特殊 token（[T1]/[T2]/[CHANGE]）嵌入作为查询，把二值变化检测与语义变化检测统一进一个生成式框架，并用文本提示替代预定义分类头以兼容类别定义冲突的多源数据，为遥感变化检测提供可复用的统一建模范式。
原文依据 We introduce three special tokens: [T1], [T2], and [CHANGE], utilising their embeddings as the key to query variations.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论变化检测（CD）是监测与分析地表覆盖动态的基础任务。尽管近期的高性能模型与高质量数据集显著推动了该领域发展，但仍存在一个关键局限。当前模型通常仅从单一类型标注数据中获取有限知识，无法同时利用多样的二值变化检测（BCD）与语义变化检测（SCD）数据集。这一约束导致泛化能力差、通用性有限。多模态大语言模型（MLLM）的最新进展为统一的变化检测框架带来了新的可能。我们利用 MLLM 的语言先验与统一能力，提出 UniChange，这是首个基于 MLLM 的统一变化检测模型。UniChange 将生成式语言能力与专门的变化检测功能相结合。我们引入三个特殊 token：[T1]、[T2] 与 [CHANGE]，利用它们的嵌入作为查询变化的键。该方法成功兼容了 BCD 与 SCD 两类任务。此外，UniChange 利用文本提示引导变化类别的识别，从而摆脱了对预定义分类头的依赖。这一设计使 UniChange 能够有效地从多源数据集中获取知识，即使这些数据集的类别定义相互冲突。在四个公开基准（WHU-CD、S2Looking、LEVIR-CD+ 与 SECOND）上的实验证明了最先进的性能，分别取得 90.41、53.04、78.87 与 57.62 的 IoU 分数，超越了此前所有方法。代码已发布于 https://github.com/NKU-HLT/UniChange。
英文原文摘要 1605 字符
Change detection (CD) is a fundamental task for monitoring and analysing 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 generalisation 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 specialised CD functionalities. We introduce three special tokens: [T1], [T2], and [CHANGE], utilising their embeddings as the key to query variations. This approach successfully accommodates both BCD and SCD tasks. Furthermore, UniChange utilises 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/NKU-HLT/UniChange.