{"url":"/task/object-proposal-generation","name":"Object Proposal Generation","slug":"object-proposal-generation","description_markdown":"Object proposal generation is a preprocessing technique that has been widely used in current object detection pipelines to guide the search of objects and avoid exhaustive sliding window search across images.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Multiscale Combinatorial Grouping\r\nfor Image Segmentation and Object Proposal Generation](https://arxiv.org/pdf/1503.00848v4.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":54,"papers_with_code":21,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/object-proposal-generation-on-pascal-voc-2012","slug":"object-proposal-generation-on-pascal-voc-2012","dataset":"PASCAL VOC 2012, 60 proposals per image","dataset_url":null,"rows_in_archive":3,"metrics":["Average Recall"],"first_row_in_archive_order":{"model":"MDef-DETR","paper_title":"Class-agnostic Object Detection with Multi-modal Transformer","paper_url":"/paper/multi-modal-transformers-excel-at-class","paper_date":"2021-11-22","arxiv_id":"2111.11430","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"syntology":null}},{"leaderboard":"/sota/object-proposal-generation-on-coco","slug":"object-proposal-generation-on-coco","dataset":"COCO (Common Objects in Context)","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["Average Recall"],"first_row_in_archive_order":{"model":"MDef-DETR (Off-the-shelf evaluation)","paper_title":"Class-agnostic Object Detection with Multi-modal Transformer","paper_url":"/paper/multi-modal-transformers-excel-at-class","paper_date":"2021-11-22","arxiv_id":"2111.11430","code_links":[{"title":"mmaaz60/mvits_for_class_agnostic_od","url":"https://github.com/mmaaz60/mvits_for_class_agnostic_od"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/comic2k","name":"Comic2k","full_name":"","num_papers_in_archive":29},{"url":"/dataset/cocodoom","name":"CocoDoom","full_name":"","num_papers_in_archive":4}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":21,"of":21,"tagged_in_all":54,"items":[{"url":"/paper/pointrcnn-3d-object-proposal-generation-and","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","date":"2018-12-11","arxiv_id":"1812.04244","repositories_listed":13,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/casenet-deep-category-aware-semantic-edge","title":"CASENet: Deep Category-Aware Semantic Edge Detection","date":"2017-05-27","arxiv_id":"1705.09759","repositories_listed":11,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/multi-view-3d-object-detection-network-for","title":"Multi-View 3D Object Detection Network for Autonomous Driving","date":"2016-11-23","arxiv_id":"1611.07759","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/recurrent-pixel-embedding-for-instance","title":"Recurrent Pixel Embedding for Instance Grouping","date":"2017-12-22","arxiv_id":"1712.08273","repositories_listed":2,"syntology":null},{"url":"/paper/adapting-pre-trained-vision-models-for-novel","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","date":"2024-05-28","arxiv_id":"2405.17859","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/towards-addressing-the-misalignment-of-object","title":"Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding","date":"2023-09-01","arxiv_id":"2309.00215","repositories_listed":1,"syntology":null},{"url":"/paper/fast-segment-anything","title":"Fast Segment Anything","date":"2023-06-21","arxiv_id":"2306.12156","repositories_listed":1,"syntology":null},{"url":"/paper/saliendet-a-saliency-based-feature","title":"SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving","date":"2023-05-11","arxiv_id":"2305.06940","repositories_listed":1,"syntology":null},{"url":"/paper/4d-stop-panoptic-segmentation-of-4d-lidar","title":"4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation","date":"2022-09-29","arxiv_id":"2209.14858","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/multi-modal-transformers-excel-at-class","title":"Class-agnostic Object Detection with Multi-modal Transformer","date":"2021-11-22","arxiv_id":"2111.11430","repositories_listed":1,"syntology":null},{"url":"/paper/superpixel-based-refinement-for-object","title":"Superpixel-based Refinement for Object Proposal Generation","date":"2021-01-12","arxiv_id":"2101.04574","repositories_listed":1,"syntology":null},{"url":"/paper/3d-object-detection-with-pointformer","title":"3D Object Detection with Pointformer","date":"2020-12-21","arxiv_id":"2012.11409","repositories_listed":1,"syntology":null},{"url":"/paper/uwsod-toward-fully-supervised-level-capacity","title":"UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attentionmask-attentive-efficient-object","title":"AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects","date":"2018-11-21","arxiv_id":"1811.08728","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-edge-detection-with-diverse-deep","title":"Semantic Edge Detection with Diverse Deep Supervision","date":"2018-04-09","arxiv_id":"1804.02864","repositories_listed":1,"syntology":null},{"url":"/paper/object-proposal-generation-applying-the","title":"Object proposal generation applying the distance dependent Chinese restaurant process","date":"2017-04-12","arxiv_id":"1704.03706","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-instance-segmentation-via-deep","title":"Semantic Instance Segmentation via Deep Metric Learning","date":"2017-03-30","arxiv_id":"1703.10277","repositories_listed":1,"syntology":null},{"url":"/paper/selective-convolutional-descriptor","title":"Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval","date":"2016-04-18","arxiv_id":"1604.04994","repositories_listed":1,"syntology":null},{"url":"/paper/seq-nms-for-video-object-detection","title":"Seq-NMS for Video Object Detection","date":"2016-02-26","arxiv_id":"1602.08465","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/convolutional-channel-features","title":"Convolutional Channel Features","date":"2015-04-28","arxiv_id":"1504.07339","repositories_listed":1,"syntology":null},{"url":"/paper/multiscale-combinatorial-grouping-for-image","title":"Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation","date":"2015-03-03","arxiv_id":"1503.00848","repositories_listed":1,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}