{"url":"/method/levit-attention-block","slug":"levit-attention-block","name":"LeViT Attention Block","full_name":"LeViT Attention Block","full_name_withheld":false,"description_markdown":"**LeViT Attention Block** is a module used for [attention](https://paperswithcode.com/methods/category/attention-mechanisms) in the [LeViT](https://paperswithcode.com/method/levit) architecture. Its main feature is providing positional information within each attention block, i.e. where we explicitly inject relative position information in the attention mechanism. This is achieved by adding an attention bias to the attention maps.","description_state":"present","introduced_year":null,"introduced_by":{"title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","paper":"/paper/levit-a-vision-transformer-in-convnet-s","first_author":"Ben Graham","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/levit-a-vision-transformer-in-convnet-s"},"source":{"url":"https://arxiv.org/abs/2104.01136v2","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Attention Modules","url":"/methods/category/attention-modules","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/learning-cortical-anomaly-through-masked","title":"Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping","date":"2023-12-05","arxiv_id":"2312.02762","n_code_links":1,"syntology":null},{"paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","arxiv_id":"2104.01136","n_code_links":12,"syntology":{"ran":23,"of":30,"unverified":7,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2021","papers":1},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/levit-attention-block"},"syntology_read_at":"2026-09-25T09:33:49+00:00"}