# SWIFT: A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening

arXiv: https://arxiv.org/abs/2507.20311 · HTML: https://mlsanity.com/paper/2507.20311/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Unsupervised Hyperspectral Pansharpening via Low-rank Diffusion Model](https://mlsanity.com/paper/2305.10925/) (2023)
- [U2Net: A General Framework with Spatial-Spectral-Integrated Double U-Net for Image Fusion](https://mlsanity.com/paper/2212.06466/) (2022)
- [FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics](https://mlsanity.com/paper/1612.05360/) (2016)
- [PanFlowNet: A Flow-Based Deep Network for Pan-sharpening](https://mlsanity.com/paper/2305.07774/) (2023)
- [SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening](https://mlsanity.com/paper/2404.11537/) (2024)
- [Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening](https://mlsanity.com/paper/2502.04903/) (2025)
- [A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening](https://mlsanity.com/paper/2503.13214/) (2025)
- [PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening](https://mlsanity.com/paper/2409.06980/) (2024)

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

- [DMAConv: Dual Mask-Adaptive Convolution for Remote Sensing Pansharpening](https://mlsanity.com/paper/2512.08331/) (2025)
- [Euler-inspired Decoupling Neural Operator for Efficient Pansharpening](https://mlsanity.com/paper/2604.12463/) (2026)

## Abstract (arXiv)

Pansharpening aims to fuse high-resolution panchromatic (PAN) images with low-resolution multispectral (LRMS) images to generate high-resolution multispectral (HRMS) images. Although deep learning-based methods have achieved promising performance, they generally suffer from severe performance degradation when applied to data from unseen sensors. Adapting these models through full-scale retraining or designing more complex architectures is often prohibitively expensive and impractical for real-world deployment. To address this critical challenge, we propose a fast and general-purpose framework for cross-sensor adaptation, SWIFT (Sensitive Weight Identification for Fast Transfer). Specifically, SWIFT employs an unsupervised sampling strategy based on data manifold structures to balance sample selection while mitigating the bias of traditional Farthest Point Sampling, efficiently selecting only 3% of the most informative samples from the target domain. This subset is then used to probe a source-domain pre-trained model by analyzing the gradient behavior of its parameters, allowing for the quick identification and subsequent update of only the weight subset most sensitive to the domain shift. As a plug-and-play framework, SWIFT can be applied to various existing pansharpening models. Extensive experiments demonstrate that SWIFT reduces the adaptation time from hours to approximately one minute on a single NVIDIA RTX 4090 GPU. The adapted models not only substantially outperform direct-transfer baselines but also achieve performance competitive with, and in some cases superior to, full retraining, establishing a new state-of-the-art on cross-sensor pansharpening tasks for the WorldView-2 and QuickBird datasets.