Paying Attention to Multiscale Feature Maps in Multimodal Image Matching
Published in
arXiv.org(2020)External Links:
TL
TL;DR
This work proposes an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN, and introduces an attentionresidual architecture, using a residual connection bypassing the encoder.