{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/paying-attention-to-multiscale-feature-maps","title":"Attention-Based Multimodal Image Matching","arxiv_id":"2103.11247","date":"2021-03-20","proceeding":null,"authors":["Aviad Moreshet","Yosi Keller"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2103.11247v2","url_pdf":"https://arxiv.org/pdf/2103.11247v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"paying-attention-to-multiscale-feature-maps","repo_url":"https://github.com/CodeJjang/multiscale-attention-patch-matching","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multimodal-patch-matching","task_name":"Multimodal Patch Matching"},{"task_slug":"patch-matching","task_name":"Patch Matching"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-patch-matching-on-visnir","task":"Multimodal Patch Matching","dataset":"VisNir","model":"Multiscale Transformer Encoder","rank_in_archive_order":1,"of":1,"metrics":{"FPR95":"1.44"},"uses_additional_data":false},{"leaderboard":"/sota/patch-matching-on-brown-dataset","task":"Patch Matching","dataset":"Brown Dataset","model":"Multiscale Transformer Encoder","rank_in_archive_order":1,"of":2,"metrics":{"FPR95":"0.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.11247","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}