{"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/superpixel-convolutional-networks-using","title":"Superpixel Convolutional Networks using Bilateral Inceptions","arxiv_id":"1511.06739","date":"2015-11-20","proceeding":null,"authors":["Raghudeep Gadde","Varun Jampani","Martin Kiefel","Daniel Kappler","Peter V. Gehler"],"abstract":"In this paper we propose a CNN architecture for semantic image segmentation.\nWe introduce a new 'bilateral inception' module that can be inserted in\nexisting CNN architectures and performs bilateral filtering, at multiple\nfeature-scales, between superpixels in an image. The feature spaces for\nbilateral filtering and other parameters of the module are learned end-to-end\nusing standard backpropagation techniques. The bilateral inception module\naddresses two issues that arise with general CNN segmentation architectures.\nFirst, this module propagates information between (super) pixels while\nrespecting image edges, thus using the structured information of the problem\nfor improved results. Second, the layer recovers a full resolution segmentation\nresult from the lower resolution solution of a CNN. In the experiments, we\nmodify several existing CNN architectures by inserting our inception module\nbetween the last CNN (1x1 convolution) layers. Empirical results on three\ndifferent datasets show reliable improvements not only in comparison to the\nbaseline networks, but also in comparison to several dense-pixel prediction\ntechniques such as CRFs, while being competitive in time.","url_abs":"http://arxiv.org/abs/1511.06739v5","url_pdf":"http://arxiv.org/pdf/1511.06739v5.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":"superpixel-convolutional-networks-using","repo_url":"https://github.com/raghudeep/bilateralinceptions","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"superpixels","task_name":"Superpixels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06739","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}