{"url":"/sota/object-proposal-generation-on-pascal-voc-2012","task":{"name":"Object Proposal Generation","url":"/task/object-proposal-generation","note":null},"dataset":{"name":"PASCAL VOC 2012, 60 proposals per image","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Average Recall"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Recall":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MDef-DETR","metrics":{"Average Recall":"0.9126"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/multi-modal-transformers-excel-at-class","paper_url":"https://arxiv.org/abs/2111.11430v6","paper_title":"Class-agnostic Object Detection with Multi-modal Transformer","code":"https://github.com/mmaaz60/mvits_for_class_agnostic_od","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Recurrent Pixel Embedding","metrics":{"Average Recall":"0.814"},"uses_additional_data":false,"paper_date":"2017-12-22","paper":"/paper/recurrent-pixel-embedding-for-instance","paper_url":"http://arxiv.org/abs/1712.08273v1","paper_title":"Recurrent Pixel Embedding for Instance Grouping","code":"https://github.com/aimerykong/Recurrent-Pixel-Embedding-for-Instance-Grouping","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"inst-DML","metrics":{"Average Recall":"0.667"},"uses_additional_data":false,"paper_date":"2017-03-30","paper":"/paper/semantic-instance-segmentation-via-deep","paper_url":"http://arxiv.org/abs/1703.10277v1","paper_title":"Semantic Instance Segmentation via Deep Metric Learning","code":"https://github.com/alicranck/instance-seg","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}