{"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/tiny-and-efficient-model-for-the-edge","title":"Tiny and Efficient Model for the Edge Detection Generalization","arxiv_id":"2308.06468","date":"2023-08-12","proceeding":null,"authors":["Xavier Soria","Yachuan Li","Mohammad Rouhani","Angel D. Sappa"],"abstract":"Most high-level computer vision tasks rely on low-level image operations as their initial processes. Operations such as edge detection, image enhancement, and super-resolution, provide the foundations for higher level image analysis. In this work we address the edge detection considering three main objectives: simplicity, efficiency, and generalization since current state-of-the-art (SOTA) edge detection models are increased in complexity for better accuracy. To achieve this, we present Tiny and Efficient Edge Detector (TEED), a light convolutional neural network with only $58K$ parameters, less than $0.2$% of the state-of-the-art models. Training on the BIPED dataset takes $less than 30 minutes$, with each epoch requiring $less than 5 minutes$. Our proposed model is easy to train and it quickly converges within very first few epochs, while the predicted edge-maps are crisp and of high quality. Additionally, we propose a new dataset to test the generalization of edge detection, which comprises samples from popular images used in edge detection and image segmentation. The source code is available in https://github.com/xavysp/TEED.","url_abs":"https://arxiv.org/abs/2308.06468v1","url_pdf":"https://arxiv.org/pdf/2308.06468v1.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":"tiny-and-efficient-model-for-the-edge","repo_url":"https://github.com/xavysp/teed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"contour-detection","task_name":"Contour Detection"},{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"uded","name":"UDED","full_name":"Unified Dataset for Edge Detection"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/edge-detection-on-uded","task":"Edge Detection","dataset":"UDED","model":"TEED","rank_in_archive_order":2,"of":5,"metrics":{"ODS":"0.828"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.06468","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}