{"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/class-independent-sequential-full-image","title":"Class-independent sequential full image segmentation, using a convolutional net that finds a segment within an attention region, given a pointer pixel within this segment","arxiv_id":"1902.07810","date":"2019-02-20","proceeding":null,"authors":["Sagi Eppel"],"abstract":"This work examines the use of a fully convolutional net (FCN) to find an\nimage segment, given a pixel within this segment region. The net receives an\nimage, a point in the image and a region of interest (RoI ) mask. The net\noutput is a binary mask of the segment in which the point is located. The\nregion where the segment can be found is contained within the input RoI mask.\nFull image segmentation can be achieved by running this net sequentially,\nregion-by-region on the image, and stitching the output segments into a single\nsegmentation map. This simple method addresses two major challenges of image\nsegmentation: 1) Segmentation of unknown categories that were not included in\nthe training set. 2) Segmentation of both individual object instances (things)\nand non-objects (stuff), such as sky and vegetation. Hence, if the pointer\npixel is located within a person in a group, the net will output a mask that\ncovers that individual person; if the pointer point is located within the sky\nregion, the net returns the region of the sky in the image. This is true even\nif no example for sky or person appeared in the training set. The net was\ntested and trained on the COCO panoptic dataset and achieved 67% IOU for\nsegmentation of familiar classes (that were part of the net training set) and\n53% IOU for segmentation of unfamiliar classes (that were not included in the\ntraining).","url_abs":"http://arxiv.org/abs/1902.07810v2","url_pdf":"http://arxiv.org/pdf/1902.07810v2.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":"class-independent-sequential-full-image","repo_url":"https://github.com/sagieppel/Pointer-based-segmentation-find-segment-containing-given-image-point-witin-given-ROI-mask-using-CNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}