Search papers, labs, and topics across Lattice.
To bypass the limitations of external decoders and flat mask serializations in dense change detection, the authors develop QUAKE-CD, a framework that recasts dense binary change prediction into grammar-constrained, syntax-verifiable quadtree token sequences. The framework couples these hierarchical mask tokens with visually grounded chain-of-thought traces (QUAKE-CoT) and trains the model via a progressive curriculum followed by grammar-gated dual-reward reinforcement learning. On bi-temporal remote sensing benchmarks, QUAKE-CD achieves 78.31% accumulated F1, outperforming both external-decoder architectures and flat text-as-mask baselines while producing faithful reasoning.
Dense pixel-level segmentation can be performed directly inside an autoregressive token space without external decoders by serializing binary change masks into grammar-constrained quadtrees.
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.
