学习具有动态双重自注意力的图像去雨 Transformer 网络
Learning Image Deraining Transformer Network with Dynamic Dual Self-Attention
AI总结：
针对单幅图像去雨中稠密自注意力引入无关信息并造成模糊的问题，本文提出融合稠密与 top-k 稀疏注意力的 DDSA，并结合 SEFN 提升重建表示，实验验证了其有效性。
摘要：
近年来，基于 Transformer 的架构因其在建模非局部信息方面的优势，被引入到单幅图像去雨任务中。然而，现有方法倾向于基于稠密自注意力策略融合全局特征，因为该策略往往使用 queries 与 keys 之间 token 的所有相似度。事实上，这种策略会导致忽略最相关的信息，并在特征聚合过程中因不相关表示而引发模糊效应。为此，本文提出一种有效的具有动态双重自注意力（dynamic dual self-attention，DDSA）的图像去雨 Transformer，该方法结合稠密与稀疏注意力策略，以更好地促进清晰图像重建。具体而言，我们仅基于 top-k 近似计算选择最有用的相似度值，以实现稀疏注意力。此外，我们还开发了一种新颖的空间增强前馈网络（spatial-enhanced feed-forward network，SEFN），以进一步获得更准确的表示，从而实现高质量的去雨结果。在基准数据集上的大量实验证明了本文所提方法的有效性。
英文摘要：
Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense self-attention strategy since it tend to uses all similarities of the tokens between the queries and keys. In fact, this strategy leads to ignoring the most relevant information and inducing blurry effect by the irrelevant representations during the feature aggregation. To this end, this paper proposes an effective image deraining Transformer with dynamic dual self-attention (DDSA), which combines both dense and sparse attention strategies to better facilitate clear image reconstruction. Specifically, we only select the most useful similarity values based on top-k approximate calculation to achieve sparse attention. In addition, we also develop a novel spatial-enhanced feed-forward network (SEFN) to further obtain a more accurate representation for achieving high-quality derained results. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed method.
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。
