良好表征，更佳解释：卷积神经网络在基于Transformer的遥感图像描述中的作用
Good Representation, Better Explanation: Role of Convolutional Neural Networks in Transformer-Based Remote Sensing Image Captioning
AI总结：
本文系统评估了十二种CNN编码器在基于Transformer的遥感图像描述中的表现，并结合数值聚类、人工评估和搜索策略分析，证明编码器选择对描述质量具有关键影响。
摘要：
遥感图像描述（RSIC）是从遥感图像生成有意义描述的过程。近年来，该任务受到广泛关注，编码器-解码器模型成为生成有意义描述的主干架构。编码器从输入图像中提取关键视觉特征，并将其转换为紧凑表征，而解码器则利用该表征生成连贯的文本描述。近年来，基于Transformer的模型因其能够捕获长程依赖关系和上下文信息而广受欢迎。解码器在文本生成方面已得到充分探索，而编码器仍相对未被充分研究。然而，优化编码器至关重要，因为它直接影响所提取特征的丰富程度，进而影响生成描述的质量。为弥补这一不足，我们在基于Transformer的编码器框架内系统评估了十二种不同的卷积神经网络（CNN）架构，以考察它们在RSIC中的有效性。评估分为两个阶段：首先，通过数值分析根据性能将CNN划分为不同聚类；随后，由一名人类标注者从以人为中心的角度对表现最佳的CNN进行人工评估。此外，我们分析了不同搜索策略（即贪心搜索和束搜索）的影响，以确保生成最佳描述。结果凸显了编码器选择在提升描述性能中的关键作用，表明特定的CNN架构能显著提高遥感图像生成描述的质量。通过对多种编码器进行详细比较，本研究为指导基于Transformer的图像描述模型的进一步发展提供了有价值的见解。
英文摘要：
Remote Sensing Image Captioning (RSIC) is the process of generating meaningful descriptions from remote sensing images. Recently, it has gained significant attention, with encoder-decoder models serving as the backbone for generating meaningful captions. The encoder extracts essential visual features from the input image, transforming them into a compact representation, while the decoder utilizes this representation to generate coherent textual descriptions. Recently, transformer-based models have gained significant popularity due to their ability to capture long-range dependencies and contextual information. The decoder has been well explored for text generation, whereas the encoder remains relatively unexplored. However, optimizing the encoder is crucial as it directly influences the richness of extracted features, which in turn affects the quality of generated captions. To address this gap, we systematically evaluate twelve different convolutional neural network (CNN) architectures within a transformer-based encoder framework to assess their effectiveness in RSIC. The evaluation consists of two stages: first, a numerical analysis categorizes CNNs into different clusters, based on their performance. The best performing CNNs are then subjected to human evaluation from a human-centric perspective by a human annotator. Additionally, we analyze the impact of different search strategies, namely greedy search and beam search, to ensure the best caption. The results highlight the critical role of encoder selection in improving captioning performance, demonstrating that specific CNN architectures significantly enhance the quality of generated descriptions for remote sensing images. By providing a detailed comparison of multiple encoders, this study offers valuable insights to guide advances in transformer-based image captioning models.
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。
