{"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/fully-connected-deep-structured-networks","title":"Fully Connected Deep Structured Networks","arxiv_id":"1503.02351","date":"2015-03-09","proceeding":null,"authors":["Alexander G. Schwing","Raquel Urtasun"],"abstract":"Convolutional neural networks with many layers have recently been shown to\nachieve excellent results on many high-level tasks such as image\nclassification, object detection and more recently also semantic segmentation.\nParticularly for semantic segmentation, a two-stage procedure is often\nemployed. Hereby, convolutional networks are trained to provide good local\npixel-wise features for the second step being traditionally a more global\ngraphical model. In this work we unify this two-stage process into a single\njoint training algorithm. We demonstrate our method on the semantic image\nsegmentation task and show encouraging results on the challenging PASCAL VOC\n2012 dataset.","url_abs":"http://arxiv.org/abs/1503.02351v1","url_pdf":"http://arxiv.org/pdf/1503.02351v1.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":[],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lesion-segmentation-on-university-of-waterloo","task":"Lesion Segmentation","dataset":"University of Waterloo skin cancer database","model":"FCN-8s","rank_in_archive_order":3,"of":5,"metrics":{"Dice score":"0.870 ±0.063 "},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.02351","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}