arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.11247cs.CVcs.LG
收藏

基于注意力的多模态图像匹配

Attention-Based Multimodal Image Matching

Bar Ilan University(巴伊兰大学)

Aviad Moreshet, Yosi Keller

AI总结:

本文提出基于Transformer编码器和多尺度Siamese CNN的注意力方法,并引入注意力残差架构,在多模态与单模态图像匹配基准上取得最先进精度。

摘要:

我们提出了一种基于注意力的多模态图像块匹配方法,使用一个Transformer编码器来关注多尺度Siamese CNN的特征图。实验表明,我们的编码器能够高效地聚合多尺度图像嵌入,同时强调任务特定的外观不变图像线索。我们还引入了一种注意力残差架构,使用绕过编码器的残差连接。这一额外的学习信号有助于从头开始进行端到端训练。实验表明,我们的方法在多模态和单模态基准测试上均达到了新的最先进精度,说明了其广泛的适用性。据我们所知,这是Transformer编码器架构首次成功应用于多模态图像块匹配任务。

英文摘要:

We propose an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN. Our encoder is shown to efficiently aggregate multiscale image embeddings while emphasizing task-specific appearance-invariant image cues. We also introduce an attention-residual architecture, using a residual connection bypassing the encoder. This additional learning signal facilitates end-to-end training from scratch. Our approach is experimentally shown to achieve new state-of-the-art accuracy on both multimodal and single modality benchmarks, illustrating its general applicability. To the best of our knowledge, this is the first successful implementation of the Transformer encoder architecture to the multimodal image patch matching task.

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。

↑