{"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-enhanced-pairwise-conditional","title":"Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation","arxiv_id":"1805.11737","date":"2018-05-29","proceeding":null,"authors":["Li Sulimowicz","Ishfaq Ahmad","Alexander Aved"],"abstract":"Superpixel-based Higher-order Conditional Random Fields (CRFs) are effective\nin enforcing long-range consistency in pixel-wise labeling problems, such as\nsemantic segmentation. However, their major short coming is considerably longer\ntime to learn higher-order potentials and extra hyperparameters and/or weights\ncompared with pairwise models. This paper proposes a superpixel-enhanced\npairwise CRF framework that consists of the conventional pairwise as well as\nour proposed superpixel-enhanced pairwise (SP-Pairwise) potentials. SP-Pairwise\npotentials incorporate the superpixel-based higher-order cues by conditioning\non a segment filtered image and share the same set of parameters as the\nconventional pairwise potentials. Therefore, the proposed superpixel-enhanced\npairwise CRF has a lower time complexity in parameter learning and at the same\ntime it outperforms higher-order CRF in terms of inference accuracy. Moreover,\nthe new scheme takes advantage of the pre-trained pairwise models by reusing\ntheir parameters and/or weights, which provides a significant accuracy boost on\nthe basis of CRF-RNN even without training. Experiments on MSRC-21 and PASCAL\nVOC 2012 dataset confirm the effectiveness of our method.","url_abs":"http://arxiv.org/abs/1805.11737v1","url_pdf":"http://arxiv.org/pdf/1805.11737v1.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-enhanced-pairwise-conditional","repo_url":"https://github.com/liyin2015/superpixel_crfasrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"crf","method_name":"CRF"},{"method_slug":"crf-rnn","method_name":"CRF-RNN"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}