{"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/linea-fast-and-accurate-line-detection-using","title":"LINEA: Fast and Accurate Line Detection Using Scalable Transformers","arxiv_id":"2505.16264","date":"2025-05-22","proceeding":null,"authors":["Sebastian Janampa","Marios Pattichis"],"abstract":"Line detection is a basic digital image processing operation used by higher-level processing methods. Recently, transformer-based methods for line detection have proven to be more accurate than methods based on CNNs, at the expense of significantly lower inference speeds. As a result, video analysis methods that require low latencies cannot benefit from current transformer-based methods for line detection. In addition, current transformer-based models require pretraining attention mechanisms on large datasets (e.g., COCO or Object360). This paper develops a new transformer-based method that is significantly faster without requiring pretraining the attention mechanism on large datasets. We eliminate the need to pre-train the attention mechanism using a new mechanism, Deformable Line Attention (DLA). We use the term LINEA to refer to our new transformer-based method based on DLA. Extensive experiments show that LINEA is significantly faster and outperforms previous models on sAP in out-of-distribution dataset testing.","url_abs":"https://arxiv.org/abs/2505.16264v1","url_pdf":"https://arxiv.org/pdf/2505.16264v1.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":"linea-fast-and-accurate-line-detection-using","repo_url":"https://github.com/SebastianJanampa/LINEA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"line-detection","task_name":"Line Detection"},{"task_slug":"line-segment-detection","task_name":"Line Segment Detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dla","method_name":"DLA"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/line-segment-detection-on-york-urban-dataset","task":"Line Segment Detection","dataset":"York Urban Dataset","model":"LINEA-L","rank_in_archive_order":1,"of":16,"metrics":{"sAP10":"34.9","sAP15":"37.3","sAP5":"30.9"},"uses_additional_data":false},{"leaderboard":"/sota/line-segment-detection-on-york-urban-dataset","task":"Line Segment Detection","dataset":"York Urban Dataset","model":"LINEA-M","rank_in_archive_order":2,"of":16,"metrics":{"sAP10":"34.5","sAP15":"36.7","sAP5":"30.3"},"uses_additional_data":false},{"leaderboard":"/sota/line-segment-detection-on-york-urban-dataset","task":"Line Segment Detection","dataset":"York Urban Dataset","model":"LINEA-S","rank_in_archive_order":4,"of":16,"metrics":{"sAP10":"32.6","sAP15":"34.8","sAP5":"28.9"},"uses_additional_data":false},{"leaderboard":"/sota/line-segment-detection-on-york-urban-dataset","task":"Line Segment Detection","dataset":"York Urban Dataset","model":"LINEA-N","rank_in_archive_order":8,"of":16,"metrics":{"sAP10":"30.5","sAP15":"32.5","sAP5":"27.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}