Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection
This addresses the challenge of diverse annotation availability in remote sensing for applications like environmental monitoring, though it is incremental as it builds on existing change detection methods.
The paper tackles the problem of expensive pixel-level labels and model adaptability in remote sensing change detection by proposing UniCD, a unified framework that handles supervised, weakly-supervised, and unsupervised tasks, achieving accuracy improvements of 12.72% and 12.37% over state-of-the-art methods in weakly and unsupervised scenarios on LEVIR-CD.
Change detection (CD) aims to identify surface changes from multi-temporal remote sensing imagery. In real-world scenarios, Pixel-level change labels are expensive to acquire, and existing models struggle to adapt to scenarios with diverse annotation availability. To tackle this challenge, we propose a unified change detection framework (UniCD), which collaboratively handles supervised, weakly-supervised, and unsupervised tasks through a coupled architecture. UniCD eliminates architectural barriers through a shared encoder and multi-branch collaborative learning mechanism, achieving deep coupling of heterogeneous supervision signals. Specifically, UniCD consists of three supervision-specific branches. In the supervision branch, UniCD introduces the spatial-temporal awareness module (STAM), achieving efficient synergistic fusion of bi-temporal features. In the weakly-supervised branch, we construct change representation regularization (CRR), which steers model convergence from coarse-grained activations toward coherent and separable change modeling. In the unsupervised branch, we propose semantic prior-driven change inference (SPCI), which transforms unsupervised tasks into controlled weakly-supervised path optimization. Experiments on mainstream datasets demonstrate that UniCD achieves optimal performance across three tasks. It exhibits significant accuracy improvements in weakly and unsupervised scenarios, surpassing current state-of-the-art by 12.72% and 12.37% on LEVIR-CD, respectively.