{"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/edge-augmentation-for-large-scale-sketch","title":"Edge Augmentation for Large-Scale Sketch Recognition without Sketches","arxiv_id":"2202.13164","date":"2022-02-26","proceeding":null,"authors":["Nikos Efthymiadis","Giorgos Tolias","Ondrej Chum"],"abstract":"This work addresses scaling up the sketch classification task into a large number of categories. Collecting sketches for training is a slow and tedious process that has so far precluded any attempts to large-scale sketch recognition. We overcome the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain. To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images. Randomization is introduced in the parameters of edge detection and edge selection. Natural images are translated to a pseudo-novel domain called \"randomized Binary Thin Edges\" (rBTE), which is used as a training domain instead of natural images. The ability to scale up is demonstrated by training CNN-based sketch recognition of more than 2.5 times larger number of categories than used previously. For this purpose, a dataset of natural images from 874 categories is constructed by combining a number of popular computer vision datasets. The categories are selected to be suitable for sketch recognition. To estimate the performance, a subset of 393 categories with sketches is also collected.","url_abs":"https://arxiv.org/abs/2202.13164v2","url_pdf":"https://arxiv.org/pdf/2202.13164v2.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":"edge-augmentation-for-large-scale-sketch","repo_url":"https://github.com/nikosefth/im2rbte","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"image-to-sketch-recognition","task_name":"Image to sketch recognition"},{"task_slug":"sketch-recognition","task_name":"Sketch Recognition"}],"methods":[],"datasets_introduced":[{"slug":"im4sketch","name":"Im4Sketch","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-sketch-recognition-on-im4sketch","task":"Image to sketch recognition","dataset":"Im4Sketch","model":"rBTE (ResNet101)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"11.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-sketch-recognition-on-im4sketch","task":"Image to sketch recognition","dataset":"Im4Sketch","model":"ResNet101","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"5.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-sketch-recognition-on-pacs","task":"Image to sketch recognition","dataset":"PACS","model":"rBTE (ResNet18)","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy":"70.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-sketch-recognition-on-sketchy","task":"Image to sketch recognition","dataset":"Sketchy","model":"rBTE (ResNet101)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"57.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-sketch-recognition-on-sketchy","task":"Image to sketch recognition","dataset":"Sketchy","model":"ResNet101","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"11.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}