一种用于遥感领域的高效且有效的编码器模型
An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain
AI总结：
本文提出了一种高效且紧凑的编码器模型，用于处理遥感领域的多任务学习，包括图像文本生成和跨模态检索。
摘要：
遥感领域最近出现了基于大视觉和语言模型（LVLMs）的方法，能够处理计算机视觉和自然语言处理交叉领域的多个任务。为了充分利用此类模型的潜力，研究重点放在了收集大量涵盖多种遥感特定任务的训练数据上，例如图像描述或视觉问答。然而，使用和训练LVLMs的成本很高，因为参数数量庞大。尽管已经探索了多种参数高效适应技术，但这些模型的训练和推理计算成本仍然对大多数机构来说是不可接受的。在本工作中，我们探讨了使用仅编码器架构，并提出了一种能够在保持参数数量紧凑的同时有效处理多任务学习的模型。特别是，我们的模型处理了通常在统一模型中未被探索的任务组合：从遥感图像生成文本和跨模态检索。我们GeoMELT模型（命名来自多任务高效学习转换器）在已建立的基准测试中的结果证实了所提出方法的有效性和效率。
英文摘要：
The remote sensing community has recently seen the emergence of methods based on Large Vision and Language Models (LVLMs) that can address multiple tasks at the intersection of computer vision and natural language processing. To fully exploit the potential of such models, a significant focus has been given to the collection of large amounts of training data that cover multiple remote sensing-specific tasks, such as image captioning or visual question answering. However, the cost of using and training LVLMs is high, due to the large number of parameters. While multiple parameter-efficient adaptation techniques have been explored, the computational costs of training and inference with these models can remain prohibitive for most institutions. In this work, we explore the use of encoder-only architectures and propose a model that can effectively address multi-task learning while remaining compact in terms of the number of parameters. In particular, our model tackles combinations of tasks that are not typically explored in a unified model: the generation of text from remote sensing images and cross-modal retrieval. The results of our GeoMELT model - named from Multi-task Efficient Learning Transformer - in established benchmarks confirm the efficacy and efficiency of the proposed approach.
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。
