# Zero-OVCD: Bridging Training-Free Foundation Models and Pseudo-Label Learning for Open-Vocabulary Change Detection

arXiv: https://arxiv.org/abs/2608.11663 · HTML: https://mlsanity.com/paper/2608.11663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 57 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [A Transformer-Based Siamese Network for Change Detection](https://mlsanity.com/paper/2201.01293/) (2022)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model](https://mlsanity.com/paper/2404.03425/) (2024)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [S2Looking: A Satellite Side-Looking Dataset for Building Change Detection](https://mlsanity.com/paper/2107.09244/) (2021)
- [Aligning and Prompting Everything All at Once for Universal Visual Perception](https://mlsanity.com/paper/2312.02153/) (2023)
- [Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images](https://mlsanity.com/paper/2309.01429/) (2023)
- [CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection](https://mlsanity.com/paper/2406.04207/) (2024)
- [Segment Any Change](https://mlsanity.com/paper/2402.01188/) (2024)
- [SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images](https://mlsanity.com/paper/2410.01768/) (2024)
- [Unsupervised Change Detection Based on Image Reconstruction Loss](https://mlsanity.com/paper/2204.01200/) (2022)
- [Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildings](https://mlsanity.com/paper/2312.16410/) (2023)
- [DynamicEarth: How Far are We from Open-Vocabulary Change Detection?](https://mlsanity.com/paper/2501.12931/) (2025)
- [Exchange means change: an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange](https://mlsanity.com/paper/2310.00689/) (2023)
- [SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2512.08730/) (2025)
- [Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-vocabulary Setting](https://mlsanity.com/paper/2501.06808/) (2025)

## Abstract (arXiv)

Open-vocabulary change detection (OVCD) enables the identification of user-specified land-cover changes in bitemporal remote sensing images, but existing training-free pipelines remain vulnerable to inaccurate candidate masks, ambiguous semantic assignments, and accumulated inference errors. To address these issues, we propose Zero-OVCD, a two-stage framework that requires no pixel-level annotations from the target domain. In the first stage, high-quality change pseudo-labels are generated through complementary candidate-mask refinement, multiscale semantic similarity fusion with margin-based reliability filtering, and response-guided mask correction and completion. These components jointly suppress noisy candidates, enhance mask-level semantic discrimination, and recover missed change regions. In the second stage, a change detector is trained using the generated pseudo-labels, while checkpoint voting and high-agreement sample selection are introduced to mitigate residual pseudo-label noise. On LEVIR-CD, WHU-CD, and S2Looking, Stage I achieves F1 scores of 86.25%, 85.82%, and 50.48%, while Stage II further improves them to 88.65%, 88.85%, and 57.96%, respectively. On SECOND, the macro-average F1 across six category-wise one-vs-rest tasks increases from 47.91% to 50.92%. These results demonstrate that bridging training-free foundation-model inference with noise-aware pseudo-label learning provides an effective solution for open-vocabulary change detection without target-domain pixel-level annotations. Code will be available at https://github.com/1321663019/Zero-OVCD.