{"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/flood-filling-networks","title":"Flood-Filling Networks","arxiv_id":"1611.00421","date":"2016-11-01","proceeding":null,"authors":["Michał Januszewski","Jeremy Maitin-Shepard","Peter Li","Jörgen Kornfeld","Winfried Denk","Viren Jain"],"abstract":"State-of-the-art image segmentation algorithms generally consist of at least\ntwo successive and distinct computations: a boundary detection process that\nuses local image information to classify image locations as boundaries between\nobjects, followed by a pixel grouping step such as watershed or connected\ncomponents that clusters pixels into segments. Prior work has varied the\ncomplexity and approach employed in these two steps, including the\nincorporation of multi-layer neural networks to perform boundary prediction,\nand the use of global optimizations during pixel clustering. We propose a\nunified and end-to-end trainable machine learning approach, flood-filling\nnetworks, in which a recurrent 3d convolutional network directly produces\nindividual segments from a raw image. The proposed approach robustly segments\nimages with an unknown and variable number of objects as well as highly\nvariable object sizes. We demonstrate the approach on a challenging 3d image\nsegmentation task, connectomic reconstruction from volume electron microscopy\ndata, on which flood-filling neural networks substantially improve accuracy\nover other state-of-the-art methods. The proposed approach can replace complex\nmulti-step segmentation pipelines with a single neural network that is learned\nend-to-end.","url_abs":"http://arxiv.org/abs/1611.00421v1","url_pdf":"http://arxiv.org/pdf/1611.00421v1.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":"flood-filling-networks","repo_url":"https://github.com/Animadversio/FloodFillNetwork-Notes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"flood-filling-networks","repo_url":"https://github.com/drewlinsley/ffn_membrane","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"flood-filling-networks","repo_url":"https://github.com/google/ffn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}