{"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-every-thing","title":"Learning to Segment Every Thing","arxiv_id":"1711.10370","date":"2017-11-28","proceeding":"CVPR 2018 6","authors":["Ronghang Hu","Piotr Dollár","Kaiming He","Trevor Darrell","Ross Girshick"],"abstract":"Most methods for object instance segmentation require all training examples\nto be labeled with segmentation masks. This requirement makes it expensive to\nannotate new categories and has restricted instance segmentation models to ~100\nwell-annotated classes. The goal of this paper is to propose a new partially\nsupervised training paradigm, together with a novel weight transfer function,\nthat enables training instance segmentation models on a large set of categories\nall of which have box annotations, but only a small fraction of which have mask\nannotations. These contributions allow us to train Mask R-CNN to detect and\nsegment 3000 visual concepts using box annotations from the Visual Genome\ndataset and mask annotations from the 80 classes in the COCO dataset. We\nevaluate our approach in a controlled study on the COCO dataset. This work is a\nfirst step towards instance segmentation models that have broad comprehension\nof the visual world.","url_abs":"http://arxiv.org/abs/1711.10370v2","url_pdf":"http://arxiv.org/pdf/1711.10370v2.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-every-thing","repo_url":"https://github.com/facebookresearch/detectron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-segment-every-thing","repo_url":"https://github.com/jiajunhua/facebookresearch-Detectron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"learning-to-segment-every-thing","repo_url":"https://github.com/ronghanghu/seg_every_thing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10370"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ronghanghu/seg_every_thing","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiajunhua/facebookresearch-Detectron","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/detectron","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8bcd17058a0b5ddd","entry":"concat_cls_score_bbox_pred","repo":"ronghanghu/seg_every_thing","repo_kind":"listed","path":"lib/modeling/mask_rcnn_heads.py","file_url":"https://github.com/ronghanghu/seg_every_thing/blob/HEAD/lib/modeling/mask_rcnn_heads.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8bcd17058a0b5ddd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}