SALT: State-Aligned Low-Rank Transfer for Single-Temporal Cross-Dataset Structural Localization in Remote Sensing

Aggelos Psiris, Georgios Angelidis, Giorgos Sfikas, Maria Vakalopoulou, Thomas Lagkas, Panagiotis Sarigiannidis, Georgios Th. PapadopoulosarXiv 2026 · arXiv

TL;DR

SALT (State-Aligned Low-Rank Transfer) enables high-performance structural localization in remote sensing using only a single image, bypassing the conventional requirement for perfectly aligned "before and after" imagery. By constraining feature adaptation to a tiny rank-2 subspace defined by learned structural states, it achieves state-of-the-art cross-dataset generalization with up to 465x fewer trainable parameters than existing baselines.

What Problem Does This Paper Address?

Change detection in remote sensing typically relies on bi-temporal imagery: two spatially aligned images of the same area taken at different times. In the real world, this is a luxury. Historical "pre-event" images are often unavailable, outdated, or impossible to align perfectly due to different sensor angles or lighting conditions.

To solve this, researchers have turned to single-temporal structural localization. Instead of looking for differences between two images, the model learns to identify structural evidence (like buildings) from a labeled source dataset and applies that knowledge to a new, unseen target image.

The catch? Over-specialization. When you adapt a powerful pretrained model (like a Vision Transformer) to a specific source dataset, it often "forgets" the general features that allow it to work on other datasets. This paper tackles the challenge of learning task-specific structural information without destroying the model's ability to generalize across different geographic regions and sensor types.

Methods

The authors introduce SALT, a framework that keeps a massive foundation model (DINOv3) frozen and only trains a tiny "adapter" layer.

  1. Structural State Modeling: The model learns two vectors in the feature space: a "positive" state ($s_P$) representing the target structure (e.g., a building) and a "negative" state ($s_N$) representing the background.
  2. State-Aligned Low-Rank Adaptation (SALA): This is the core innovation. Instead of allowing the model to change features in any direction, SALA restricts corrections to the rank-2 subspace (a 2D plane) spanned by the positive and negative states. This ensures that feature adaptation is directly coupled with the final prediction task.
  3. Directional State Alignment (DSA): A specialized loss function that "nudges" patch features. It encourages patches containing buildings to move toward the positive state and background patches to move toward the negative state.
  4. Geometry Preservation: To prevent the model from distorting the rich visual relationships learned by the frozen backbone, SALT uses a loss that ensures the pairwise similarity between patches remains consistent before and after adaptation.
Overview of the SALT architecture, showing how patch features are projected and corrected within a state-defined plane.

Datasets

The researchers evaluated SALT on two prominent remote sensing benchmarks:

  • LEVIR-CD: Originally a change detection dataset, used here for its building-change annotations.
  • WHU Aerial Building Dataset: Focused on building footprints.

The experiments were strictly cross-dataset: the model was trained on one dataset and tested on the other without any further tuning or "peeking" at the target data. This is a rigorous test of true generalization.

Key Insights and Ideas

  • Less is More: By restricting adaptation to a rank-2 subspace, SALT prevents the "feature drift" that plagues larger adapters. It turns out that if you define your adaptation space using the same states you use for prediction, you don't need millions of parameters to get high accuracy.
  • Foundation Models are Robust: The results suggest that foundation models like DINOv3 already contain most of the information needed for structural localization. We don't need to "retrain" them; we just need to "align" their existing features to our specific task.
  • Coupling is Key: Most existing methods learn how to adapt features independently of what they are predicting. SALT’s "state-alignment" ensures that every bit of training effort is spent moving features in directions that actually matter for the final classification.

Key Results

SALT significantly outperformed four recent baselines while being orders of magnitude more efficient.

  • Accuracy: In the LEVIR-CD $\rightarrow$ WHU transfer direction, SALT improved pixel-level Average Precision (AP) by 9.45 points and Intersection-over-Union (IoU) by a staggering 27.69 points over the strongest baseline.
  • Efficiency: SALT uses only 0.068M trainable parameters. As shown in Figure 1, this is 69x to 465x fewer than competing methods like VisualAD or MoECLIP.
  • Speed: The model processes images in just 40.2 ms, making it highly suitable for real-time monitoring or large-scale planetary analysis.
Performance vs. Adaptation Size. SALT (red) achieves the highest accuracy with the fewest parameters.

Qualitatively, SALT produces much cleaner and more complete localization maps compared to baselines, which often produce fragmented or noisy results under cross-dataset shifts.

Figure 3. Indicative cross-dataset localization results. Rows are labeled by the target dataset (WHU rows from LEVIR-CD→WHU, LEVIR rows from WHU→LEVIR-CD, with LEVIR denoting LEVIR-CD). For each method, the heatmap shows the dense response map and the binary mask uses the threshold selected on the source validation split.

Limitations and Future Work

While SALT is highly effective, the authors note a few areas for improvement:

  • State Complexity: Using only a single pair of positive/negative states might be too simple for datasets with highly heterogeneous structures (e.g., very different architectural styles).
  • Temporal Ambiguity: Because it only uses one image, the model cannot distinguish between a new building and an old building—it only sees "a building."
  • Future Directions: The authors suggest exploring multi-context states and adaptive-rank adaptation to handle even more complex environmental shifts.

Summary updated

Abstract

Change detection in remote sensing conventionally relies on spatially aligned bi-temporal imagery, which may be unavailable or unreliable in practical scenarios. Recent single-temporal approaches address this limitation by learning structural evidence, such as building regions, from a labeled source dataset and transferring it to unseen target imagery using only the current image. However, adaptation to the source dataset can over-specialize pretrained features and reduce their cross-dataset generalization, a risk that this paper argues is higher when the feature adaptation is parameterized independently of the states used for prediction. To address this issue, the current study introduces SALT, a State-Aligned Low-Rank Transfer framework. SALT keeps a DINOv3 backbone frozen and learns negative and positive structural states that both score each patch and, through State-Aligned Low-Rank Adaptation (SALA), span the rank-2 subspace in which patch features are corrected. Directional State Alignment supervises these corrections to raise the evidence of positive patches and lower that of negative ones, while Geometry Preservation limits changes to the pairwise relations among pretrained patch features. Experiments on LEVIR-CD and the WHU aerial building dataset show that, at the pixel level and in both transfer directions, SALT outperforms four baselines reproduced under a common source-only protocol, improving over the strongest reproduced baselines by 9.45 and 5.79 points in pixel-level AP and by 27.69 and 14.25 points in IoU (LEVIR-CD to WHU and WHU to LEVIR-CD, respectively), with only 0.068M trainable parameters and 40.2 ms per image. In order to facilitate reproducibility and further research, the source code of SALT is available at https://github.com/gthpapadopoulos/SALT
BibTeX
@misc{psiris2026salt,
  author = {Aggelos Psiris and Georgios Angelidis and Giorgos Sfikas and Maria Vakalopoulou and Thomas Lagkas and Panagiotis Sarigiannidis and Georgios Th. Papadopoulos},
  title = {{SALT: State-Aligned Low-Rank Transfer for Single-Temporal Cross-Dataset Structural Localization in Remote Sensing}},
  year = {2026},
  eprint = {2611.17077},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.17077},
}
Figure