From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection

2026-09-09

AI Summary

本文提出QUAKE-CD框架，通过将变化检测结果编码为语法约束的四叉树序列，改进了视觉-语言模型在像素级变化检测中的表现，特别是在处理小而分散的变化时。

Abstract

Dense change detection in remote sensing requires vision-language models (VLMs) to compare bi-temporal images and generate accurate pixel-level masks. Existing VLMs are largely confined to change captioning outputs, and the few that produce pixel-level masks still rely on external decoders or flat text-as-mask serialization, which are less effective for small and fragmented changes. We introduce QUAKE-CD, a framework that recasts dense change prediction as syntax-verifiable structured generation. QUAKE-CD represents binary change masks as grammar-constrained quadtree token sequences, making the masks compact, syntactically checkable, and deterministically decodable within an autoregressive generation space. We further construct QUAKE-CoT, which pairs these sequences with chain-of-thought traces grounded in visual evidence, and jointly optimizes textual reasoning and spatial dense prediction through a progressive curriculum followed by grammar-gated dual-reward RL. On QUAKE-CoT, QUAKE-CD achieves 78.31% accumulated F1, outperforming decoder-based and flat text-as-mask VLMs while producing more faithful bi-temporal reasoning.

Problem

• dense change detection
• vision-language models
• pixel-level masks
• external decoders
• text-as-mask serialization

Innovation

• QUAKE-CD
• quadtree encoding
• syntax-verifiable structured generation
• grammar-gated dual-reward RL