# MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification

arXiv: https://arxiv.org/abs/2604.26774 · HTML: https://mlsanity.com/paper/2604.26774/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community](https://mlsanity.com/paper/2408.09110/) (2024)
- [CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection](https://mlsanity.com/paper/2406.04207/) (2024)
- [Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images](https://mlsanity.com/paper/1812.00645/) (2018)
- [Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing](https://mlsanity.com/paper/2509.12040/) (2025)
- [DynamicEarth: How Far are We from Open-Vocabulary Change Detection?](https://mlsanity.com/paper/2501.12931/) (2025)
- [Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-vocabulary Setting](https://mlsanity.com/paper/2501.06808/) (2025)
- [UniVCD: A New Method for Unsupervised Change Detection in the Open-Vocabulary Era](https://mlsanity.com/paper/2512.13089/) (2025)
- [AdaptOVCD: Training-Free Open-Vocabulary Remote Sensing Change Detection via Adaptive Information Fusion](https://mlsanity.com/paper/2602.06529/) (2026)
- [OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3](https://mlsanity.com/paper/2601.13895/) (2026)
- [Dual-branch Spatial-Temporal Self-supervised Representation for Enhanced Road Network Learning](https://mlsanity.com/paper/2511.06633/) (2025)

## Built on by (most cited first, 2 of 2)

- [CogVis: Must Open-Vocabulary Change Detection Perceive the Scene Anew for Every Query?](https://mlsanity.com/paper/2608.06150/) (2026)
- [Zero-OVCD: Bridging Training-Free Foundation Models and Pseudo-Label Learning for Open-Vocabulary Change Detection](https://mlsanity.com/paper/2608.11663/) (2026)

## Abstract (arXiv)

Open-vocabulary change detection aims to identify semantic changes in bi-temporal remote sensing images without predefined categories. Recent methods combine foundation models such as SAM, DINO and CLIP, but typically process each timestamp independently or interact only at the final comparison stage. Such paradigms suffer from insufficient temporal coupling during semantic reasoning, which limits their ability to distinguish genuine semantic changes from non-semantic appearance discrepancies. In addition, patch-dominant inference on high-resolution images often weakens global semantic continuity and produces fragmented change regions. To address these issues, we propose MemOVCD, a training-free open-vocabulary change detection framework based on cross-temporal memory reasoning and global-local adaptive rectification. Specifically, we reformulate bi-temporal change detection as a two-frame tracking problem and introduce weighted bidirectional propagation to aggregate semantic evidence from both temporal directions. To stabilize memory propagation across large temporal gaps, we construct histogram-aligned transition frames to smooth abrupt appearance changes. Moreover, a global-local adaptive rectification strategy adaptively fuses local and global-view predictions, improving spatial consistency while preserving fine-grained details. Experiments on five benchmarks demonstrate that MemOVCD achieves favorable performance on two change detection tasks, validating its effectiveness and generalization under diverse open-vocabulary settings.