{"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/learning-to-segment-object-candidates","title":"Learning to Segment Object Candidates","arxiv_id":"1506.06204","date":"2015-06-20","proceeding":"NeurIPS 2015 12","authors":["Pedro O. Pinheiro","Ronan Collobert","Piotr Dollar"],"abstract":"Recent object detection systems rely on two critical steps: (1) a set of\nobject proposals is predicted as efficiently as possible, and (2) this set of\ncandidate proposals is then passed to an object classifier. Such approaches\nhave been shown they can be fast, while achieving the state of the art in\ndetection performance. In this paper, we propose a new way to generate object\nproposals, introducing an approach based on a discriminative convolutional\nnetwork. Our model is trained jointly with two objectives: given an image\npatch, the first part of the system outputs a class-agnostic segmentation mask,\nwhile the second part of the system outputs the likelihood of the patch being\ncentered on a full object. At test time, the model is efficiently applied on\nthe whole test image and generates a set of segmentation masks, each of them\nbeing assigned with a corresponding object likelihood score. We show that our\nmodel yields significant improvements over state-of-the-art object proposal\nalgorithms. In particular, compared to previous approaches, our model obtains\nsubstantially higher object recall using fewer proposals. We also show that our\nmodel is able to generalize to unseen categories it has not seen during\ntraining. Unlike all previous approaches for generating object masks, we do not\nrely on edges, superpixels, or any other form of low-level segmentation.","url_abs":"http://arxiv.org/abs/1506.06204v2","url_pdf":"http://arxiv.org/pdf/1506.06204v2.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":"learning-to-segment-object-candidates","repo_url":"https://github.com/aby2s/sharpmask","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-segment-object-candidates","repo_url":"https://github.com/facebookresearch/deepmask","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"superpixels","task_name":"Superpixels"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1506.06204","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}