{"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/solq-segmenting-objects-by-learning-queries","title":"SOLQ: Segmenting Objects by Learning Queries","arxiv_id":"2106.02351","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Bin Dong","Fangao Zeng","Tiancai Wang","Xiangyu Zhang","Yichen Wei"],"abstract":"In this paper, we propose an end-to-end framework for instance segmentation. Based on the recently introduced DETR [1], our method, termed SOLQ, segments objects by learning unified queries. In SOLQ, each query represents one object and has multiple representations: class, location and mask. The object queries learned perform classification, box regression and mask encoding simultaneously in an unified vector form. During training phase, the mask vectors encoded are supervised by the compression coding of raw spatial masks. In inference time, mask vectors produced can be directly transformed to spatial masks by the inverse process of compression coding. Experimental results show that SOLQ can achieve state-of-the-art performance, surpassing most of existing approaches. Moreover, the joint learning of unified query representation can greatly improve the detection performance of DETR. We hope our SOLQ can serve as a strong baseline for the Transformer-based instance segmentation. Code is available at https://github.com/megvii-research/SOLQ.","url_abs":"https://arxiv.org/abs/2106.02351v3","url_pdf":"https://arxiv.org/pdf/2106.02351v3.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":"solq-segmenting-objects-by-learning-queries","repo_url":"https://github.com/megvii-research/SOLQ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"SOLQ (Swin-L, single scale)","rank_in_archive_order":35,"of":112,"metrics":{"mask AP":"46.7"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"SOLQ (ResNet101, single scale)","rank_in_archive_order":65,"of":112,"metrics":{"mask AP":"40.9"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"SOLQ (ResNet50, single scale)","rank_in_archive_order":76,"of":112,"metrics":{"mask AP":"39.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"SOLQ (Swin-L, single scale)","rank_in_archive_order":212,"of":220,"metrics":{"AP50":"74.9","AP75":"61.3","APL":"71.9"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"SOLQ (Swin-L, single scale)","rank_in_archive_order":41,"of":225,"metrics":{"AP50":"74.6","AP75":"60.5","APL":"70.6","APM":"60","APS":"37.6","box mAP":"56.5"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"SOLQ (ResNet101, single scale)","rank_in_archive_order":103,"of":225,"metrics":{"box mAP":"48.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"SOLQ (ResNet50, single scale)","rank_in_archive_order":115,"of":225,"metrics":{"box mAP":"47.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.02351","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}