{"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/unsupervised-discovery-of-the-long-tail-in","title":"Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision","arxiv_id":"2104.01257","date":"2021-04-02","proceeding":"CVPR 2021 1","authors":["Zhenzhen Weng","Mehmet Giray Ogut","Shai Limonchik","Serena Yeung"],"abstract":"Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarchical structure between objects in the images, we propose self-supervised losses for learning mask embeddings. Trained on COCO dataset without additional annotations of the long-tail objects, our model is able to discover novel and more fine-grained objects than the common categories in COCO. We show that the model achieves competitive quantitative results on LVIS as compared to the supervised and partially supervised methods.","url_abs":"https://arxiv.org/abs/2104.01257v1","url_pdf":"https://arxiv.org/pdf/2104.01257v1.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":[],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"novel-object-detection","task_name":"Novel Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/novel-object-detection-on-lvis-v1-0-val","task":"Novel Object Detection","dataset":"LVIS v1.0 val","model":"Weng et al. Weng et al. (2021)*","rank_in_archive_order":5,"of":5,"metrics":{"All mAP":"1.62","Known mAP":"17.85","Novel mAP":"0.27"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.01257","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}