双模文本提示学习用于遥感图像的视觉-语言模型
bi-modal textual prompt learning for vision-language models in remote sensing
AI总结：
BiMoRS通过双模提示学习框架提升遥感图像视觉-语言模型的适应性与泛化能力。
摘要：
提示学习（PL）已作为一种有效策略，用于适应视觉-语言模型（VLMs），如CLIP，以适应下游任务，在有限监督下。虽然PL在自然图像数据集上表现强劲，但其在遥感（RS）图像中的可转移性仍被低估。RS数据具有独特挑战，包括多标签场景、高类内变异性以及多样的空间分辨率，这些阻碍了现有PL方法的直接应用。特别是，当前基于提示的方法往往难以识别主导的语义线索，并且在RS场景中无法推广到新类别。为了解决这些挑战，我们提出了BiMoRS，一种轻量级双模提示学习框架，专为RS任务设计。BiMoRS使用冻结的图像描述模型（例如BLIP-2）从RS图像中提取文本语义摘要。这些描述被使用BERT分词器进行分词，并与CLIP编码器的高级视觉特征融合。一个轻量级的交叉注意力模块随后将融合的文本-视觉表示条件地应用于可学习的查询提示，从而生成上下文化的提示，而不会改变CLIP主干。我们在四个RS数据集上评估了BiMoRS，跨越三个领域泛化（DG）任务，并观察到一致的性能提升，在平均情况下，比强基线高出多达2%。代码可在https://github.com/ipankhi/BiMoRS上获得。
英文摘要：
Prompt learning (PL) has emerged as an effective strategy to adapt vision-language models (VLMs), such as CLIP, for downstream tasks under limited supervision. While PL has demonstrated strong generalization on natural image datasets, its transferability to remote sensing (RS) imagery remains underexplored. RS data present unique challenges, including multi-label scenes, high intra-class variability, and diverse spatial resolutions, that hinder the direct applicability of existing PL methods. In particular, current prompt-based approaches often struggle to identify dominant semantic cues and fail to generalize to novel classes in RS scenarios. To address these challenges, we propose BiMoRS, a lightweight bi-modal prompt learning framework tailored for RS tasks. BiMoRS employs a frozen image captioning model (e.g., BLIP-2) to extract textual semantic summaries from RS images. These captions are tokenized using a BERT tokenizer and fused with high-level visual features from the CLIP encoder. A lightweight cross-attention module then conditions a learnable query prompt on the fused textual-visual representation, yielding contextualized prompts without altering the CLIP backbone. We evaluate BiMoRS on four RS datasets across three domain generalization (DG) tasks and observe consistent performance gains, outperforming strong baselines by up to 2% on average. Codes are available at https://github.com/ipankhi/BiMoRS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
