{"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/feedforward-semantic-segmentation-with-zoom","title":"Feedforward semantic segmentation with zoom-out features","arxiv_id":"1412.0774","date":"2014-12-02","proceeding":"CVPR 2015 6","authors":["Mohammadreza Mostajabi","Payman Yadollahpour","Gregory Shakhnarovich"],"abstract":"We introduce a purely feed-forward architecture for semantic segmentation. We\nmap small image elements (superpixels) to rich feature representations\nextracted from a sequence of nested regions of increasing extent. These regions\nare obtained by \"zooming out\" from the superpixel all the way to scene-level\nresolution. This approach exploits statistical structure in the image and in\nthe label space without setting up explicit structured prediction mechanisms,\nand thus avoids complex and expensive inference. Instead superpixels are\nclassified by a feedforward multilayer network. Our architecture achieves new\nstate of the art performance in semantic segmentation, obtaining 64.4% average\naccuracy on the PASCAL VOC 2012 test set.","url_abs":"http://arxiv.org/abs/1412.0774v1","url_pdf":"http://arxiv.org/pdf/1412.0774v1.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":"feedforward-semantic-segmentation-with-zoom","repo_url":"https://github.com/fhalamos/semantic-segmentation-with-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"superpixels","task_name":"Superpixels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.0774","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}