{"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-via-cut-and-paste","title":"Learning to Segment via Cut-and-Paste","arxiv_id":"1803.06414","date":"2018-03-16","proceeding":"ECCV 2018 9","authors":["Tal Remez","Jonathan Huang","Matthew Brown"],"abstract":"This paper presents a weakly-supervised approach to object instance\nsegmentation. Starting with known or predicted object bounding boxes, we learn\nobject masks by playing a game of cut-and-paste in an adversarial learning\nsetup. A mask generator takes a detection box and Faster R-CNN features, and\nconstructs a segmentation mask that is used to cut-and-paste the object into a\nnew image location. The discriminator tries to distinguish between real\nobjects, and those cut and pasted via the generator, giving a learning signal\nthat leads to improved object masks. We verify our method experimentally using\nCityscapes, COCO, and aerial image datasets, learning to segment objects\nwithout ever having seen a mask in training. Our method exceeds the performance\nof existing weakly supervised methods, without requiring hand-tuned segment\nproposals, and reaches 90% of supervised performance.","url_abs":"http://arxiv.org/abs/1803.06414v1","url_pdf":"http://arxiv.org/pdf/1803.06414v1.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-via-cut-and-paste","repo_url":"https://github.com/FLoosli/CP_GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.06414","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}