跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2601.17747 · v3

Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection

首次提交 2026-01-25 16:43
版本更新 2026-11-19 12:35
雷达观测 2026-11-20 10:50
arXiv ↗PDF ↗

摘要

Change detection (CD) identifies surface changes from bi-temporal remote sensing imagery. Depending on annotation budgets and application contexts, real-world change labels take heterogeneous forms: pixel-level masks, image-level labels, unlabeled samples, or mixtures of these supervision types. However, most existing CD methods target a single supervision paradigm and cannot leverage complex annotation scenarios. To tackle this challenge, we present UniCD, a unified change detection framework that accommodates supervised, weakly supervised, unsupervised, and mixed-supervision learning within a single network. To bridge supervision granularity gaps, we design Supervision-Anchored Cross-Granularity Prototype Propagation, which constructs class-specific prototypes from pixel-level annotations and transfers reliable change semantics to image-level labeled and unlabeled samples. We further design Multi-source Consistency Rectification to filter unreliable pseudo labels and selectively recover informative pixels through multi-source evidence and cross-view consistency. Experiments on LEVIR-CD, WHU-CD, and CLCD demonstrate that UniCD consistently outperforms conventional mixed training, improving the average IoU by 3.02 percentage points across different mixed-supervision settings, while achieving state-of-the-art performance under individual supervision settings.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-19 12:35 · 最新观测版本

Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection

Change detection (CD) identifies surface changes from bi-temporal remote sensing imagery. Depending on annotation budgets and application contexts, real-world change labels take heterogeneous forms: pixel-level masks, image-level labels, unlabeled samples, or mixtures of these supervision types. However, most existing CD methods target a single supervision paradigm and cannot leverage complex annotation scenarios. To tackle this challenge, we present UniCD, a unified change detection framework that accommodates supervised, weakly supervised, unsupervised, and mixed-supervision learning within a single network. To bridge supervision granularity gaps, we design Supervision-Anchored Cross-Granularity Prototype Propagation, which constructs class-specific prototypes from pixel-level annotations and transfers reliable change semantics to image-level labeled and unlabeled samples. We further design Multi-source Consistency Rectification to filter unreliable pseudo labels and selectively recover informative pixels through multi-source evidence and cross-view consistency. Experiments on LEVIR-CD, WHU-CD, and CLCD demonstrate that UniCD consistently outperforms conventional mixed training, improving the average IoU by 3.02 percentage points across different mixed-supervision settings, while achieving state-of-the-art performance under individual supervision settings.

查看此版本解读 →查看此版本原文 ↗