{"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/one-shot-learning-for-semantic-segmentation","title":"One-Shot Learning for Semantic Segmentation","arxiv_id":"1709.03410","date":"2017-09-11","proceeding":null,"authors":["Amirreza Shaban","Shray Bansal","Zhen Liu","Irfan Essa","Byron Boots"],"abstract":"Low-shot learning methods for image classification support learning from\nsparse data. We extend these techniques to support dense semantic image\nsegmentation. Specifically, we train a network that, given a small set of\nannotated images, produces parameters for a Fully Convolutional Network (FCN).\nWe use this FCN to perform dense pixel-level prediction on a test image for the\nnew semantic class. Our architecture shows a 25% relative meanIoU improvement\ncompared to the best baseline methods for one-shot segmentation on unseen\nclasses in the PASCAL VOC 2012 dataset and is at least 3 times faster.","url_abs":"http://arxiv.org/abs/1709.03410v1","url_pdf":"http://arxiv.org/pdf/1709.03410v1.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":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/lzzcd001/OSLSM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/RogerQi/pascal-5i","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/chunbolang/DCP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/ml4ai/mliis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/vamsirk/FewShotLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/vamsirk/OneShotSemanticSegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/woaixuexixuexi/PSANet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"one-shot-learning-for-semantic-segmentation","repo_url":"https://github.com/zwzheng98/qclnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"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":"one-shot-learning","task_name":"One-Shot Learning"},{"task_slug":"one-shot-segmentation","task_name":"One-Shot Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[{"slug":"pascal-5i","name":"PASCAL-5i","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.03410","atlas_url":"https://app.syntology.ai/?focus=1709.03410","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}