{"url":"/dataset/lvis","name":"LVIS","full_name":null,"description_markdown":"LVIS is a dataset for long tail instance segmentation. It has annotations for over 1000 object categories in 164k images.\r\n\r\nSource: [LVIS](https://arxiv.org/pdf/1908.03195.pdf)","description_withheld":null,"homepage":"https://www.lvisdataset.org/dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/lvis-a-dataset-for-large-vocabulary-instance-1","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","first_author":"Agrim Gupta","url":null},"license":{"name":"Custom (CC BY 4.0 + COCO license)","url":"https://www.lvisdataset.org/dataset"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Few-Shot Object Detection","url":"/task/few-shot-object-detection","datasets_with_task":"/datasets/task/few-shot-object-detection"},{"name":"Unsupervised Object Detection","url":"/task/unsupervised-object-detection","datasets_with_task":"/datasets/task/unsupervised-object-detection"},{"name":"Zero-Shot Object Detection","url":"/task/zero-shot-object-detection","datasets_with_task":"/datasets/task/zero-shot-object-detection"},{"name":"Open Vocabulary Object Detection","url":"/task/open-vocabulary-object-detection","datasets_with_task":"/datasets/task/open-vocabulary-object-detection"},{"name":"Long-tailed Object Detection","url":"/task/long-tailed-object-detection","datasets_with_task":"/datasets/task/long-tailed-object-detection"},{"name":"Novel Object Detection","url":"/task/novel-object-detection","datasets_with_task":"/datasets/task/novel-object-detection"},{"name":"Zero-Shot Instance Segmentation","url":"/task/zero-shot-instance-segmentation","datasets_with_task":"/datasets/task/zero-shot-instance-segmentation"}],"languages":[],"variants":["LVIS v1.0","LVIS v1.0 val","LVIS v1.0 test-dev","LVIS","LVIS v1.0 minival"],"data_loaders":[{"repo":"https://github.com/facebookresearch/detectron2","url":"https://detectron2.readthedocs.io/en/latest/tutorials/builtin_datasets.html#expected-dataset-structure-for-lvis-instance-segmentation","frameworks":["pytorch"]},{"repo":"https://github.com/open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/blob/master/docs/1_exist_data_model.md","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/lvis","frameworks":["tf","jax"]}],"num_papers_in_archive":551,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset_variant":"LVIS v1.0","rows":28,"metrics":["AP novel-LVIS base training","AP novel-Unrestricted open-vocabulary training"],"first_row_in_archive_order":{"model":"LaMI-DETR","paper":"/paper/lami-detr-open-vocabulary-detection-with","metrics":{"AP novel-LVIS base training":"43.4"},"code_links":[{"title":"eternaldolphin/lami-detr","url":"https://github.com/eternaldolphin/lami-detr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset_variant":"LVIS v1.0 val","rows":25,"metrics":["mask AP","mask APr"],"first_row_in_archive_order":{"model":"Co-DETR (single-scale)","paper":"/paper/detrs-with-collaborative-hybrid-assignments","metrics":{"mask AP":"60.7"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-val","task":"Object Detection","dataset_variant":"LVIS v1.0 val","rows":15,"metrics":["box AP","box APr"],"first_row_in_archive_order":{"model":"Co-DETR (single-scale)","paper":"/paper/detrs-with-collaborative-hybrid-assignments","metrics":{"box AP":"68.0"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0","task":"Zero-Shot Object Detection","dataset_variant":"LVIS v1.0 minival","rows":11,"metrics":["AP"],"first_row_in_archive_order":{"model":"CP-DETR-Pro(without LVIS data)","paper":"/paper/cp-detr-concept-prompt-guide-detr-toward","metrics":{"AP":"58.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0-val","task":"Zero-Shot Object Detection","dataset_variant":"LVIS v1.0 val","rows":9,"metrics":["AP"],"first_row_in_archive_order":{"model":"CP-DETR-Pro(without LVIS data)","paper":"/paper/cp-detr-concept-prompt-guide-detr-toward","metrics":{"AP":"51.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-object-detection-on-lvis-v1-0-val","task":"Few-Shot Object Detection","dataset_variant":"LVIS v1.0 val","rows":7,"metrics":["AP","AP50","AP75","APr","APc","APf"],"first_row_in_archive_order":{"model":"best_single_model_val","paper":null,"metrics":{"AP":"47.55","AP50":"63.1","AP75":"51.15","APc":"47.47","APf":"51.44","APr":"38.91"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-minival","task":"Object Detection","dataset_variant":"LVIS v1.0 minival","rows":6,"metrics":["box AP"],"first_row_in_archive_order":{"model":"Co-DETR (single-scale)","paper":"/paper/detrs-with-collaborative-hybrid-assignments","metrics":{"box AP":"72.0"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-object-detection-on-lvis-v1-0-test","task":"Few-Shot Object Detection","dataset_variant":"LVIS v1.0 test-dev","rows":5,"metrics":["AP","AP50","AP75","APr","APc","APf"],"first_row_in_archive_order":{"model":"TestConsistency","paper":null,"metrics":{"AP":"48.58","AP50":"64.14","AP75":"51.74","APc":"47.91","APf":"52.07","APr":"42.52"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/novel-object-detection-on-lvis-v1-0-val","task":"Novel Object Detection","dataset_variant":"LVIS v1.0 val","rows":5,"metrics":["All mAP","Known mAP","Novel mAP"],"first_row_in_archive_order":{"model":"Cooperative Foundational Models","paper":"/paper/enhancing-novel-object-detection-via","metrics":{"All mAP":"19.33","Known mAP":"42.08","Novel mAP":"17.42"},"code_links":[{"title":"rohit901/cooperative-foundational-models","url":"https://github.com/rohit901/cooperative-foundational-models"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-test-dev","task":"Instance Segmentation","dataset_variant":"LVIS v1.0 test-dev","rows":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"R50-FPN-MaskRCNN-TTA","paper":"/paper/1st-place-solution-of-lvis-challenge-2020-a","metrics":{"mask AP":"41.23"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-tailed-object-detection-on-lvis-v1-0-val","task":"Long-tailed Object Detection","dataset_variant":"LVIS v1.0 val","rows":1,"metrics":["mAP@0.5:0.95"],"first_row_in_archive_order":{"model":"R101 Faster R-CNN","paper":"/paper/balanced-classification-a-unified-framework","metrics":{"mAP@0.5:0.95":"27.8"},"code_links":[{"title":"tianhao-qi/bacl","url":"https://github.com/tianhao-qi/bacl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-1","task":"Object Detection","dataset_variant":"LVIS v1.0","rows":1,"metrics":[" box AP"],"first_row_in_archive_order":{"model":"ScaleDet","paper":"/paper/scaledet-a-scalable-multi-dataset-object-1","metrics":{" box AP":"50.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/simltd-simple-supervised-and-semi-supervised","title":"SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection","date":"2024-12-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/comprehensive-multi-modal-prototypes-are","title":"Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection","date":"2024-12-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cp-detr-concept-prompt-guide-detr-toward","title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","date":"2024-12-13","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/fractal-calibration-for-long-tailed-object","title":"Fractal Calibration for long-tailed object detection","date":"2024-10-15","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-parametric-activation","title":"Adaptive Parametric Activation","date":"2024-07-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ov-dino-unified-open-vocabulary-detection","title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","date":"2024-07-10","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ovmr-open-vocabulary-recognition-with-multi","title":"OVMR: Open-Vocabulary Recognition with Multi-Modal References","date":"2024-06-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rtgen-generating-region-text-pairs-for-open","title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection","date":"2024-05-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ov-dquo-open-vocabulary-detr-with-denoising","title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","date":"2024-05-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/grounding-dino-1-5-advance-the-edge-of-open","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","date":"2024-05-16","rows_on_this_dataset":6,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/divergen-improving-instance-segmentation-by","title":"DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data","date":"2024-05-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-open-vocabulary-object","title":"Retrieval-Augmented Open-Vocabulary Object Detection","date":"2024-04-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/yolo-world-real-time-open-vocabulary-object","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","date":"2024-01-30","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/clim-contrastive-language-image-mosaic-for","title":"CLIM: Contrastive Language-Image Mosaic for Region Representation","date":"2023-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":8,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/enhancing-novel-object-detection-via","title":"Enhancing Novel Object Detection via Cooperative Foundational Models","date":"2023-11-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/codet-co-occurrence-guided-region-word-1","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","date":"2023-10-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-from-rich-semantics-and-coarse","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","date":"2023-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/clipself-vision-transformer-distills-itself","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","date":"2023-10-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/detection-oriented-image-text-pretraining-for","title":"Region-centric Image-Language Pretraining for Open-Vocabulary Detection","date":"2023-09-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/detect-every-thing-with-few-examples","title":"Detect Everything with Few Examples","date":"2023-09-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":15,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/contrastive-feature-masking-open-vocabulary","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","date":"2023-09-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/balanced-classification-a-unified-framework","title":"Balanced Classification: A Unified Framework for Long-Tailed Object Detection","date":"2023-08-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scaling-open-vocabulary-object-detection-1","title":"Scaling Open-Vocabulary Object Detection","date":"2023-06-16","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/scaledet-a-scalable-multi-dataset-object-1","title":"ScaleDet: A Scalable Multi-Dataset Object Detector","date":"2023-06-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-modal-queried-object-detection-in-the","title":"Multi-modal Queried Object Detection in the Wild","date":"2023-05-30","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prompt-pre-training-with-twenty-thousand-1","title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","date":"2023-04-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/object-aware-distillation-pyramid-for-open","title":"Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection","date":"2023-03-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/grounding-dino-marrying-dino-with-grounded","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","date":"2023-03-09","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aligning-bag-of-regions-for-open-vocabulary","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","date":"2023-02-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/x-paste-revisit-copy-paste-at-scale-with-clip","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","date":"2022-12-07","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/diffusioninst-diffusion-model-for-instance","title":"DiffusionInst: Diffusion Model for Instance Segmentation","date":"2022-12-06","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":11,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/detrs-with-collaborative-hybrid-assignments","title":"DETRs with Collaborative Hybrid Assignments Training","date":"2022-11-22","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-all-in-one-pre-training-via","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","date":"2022-11-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-discover-and-detect-objects","title":"Learning to Discover and Detect Objects","date":"2022-10-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/long-tailed-instance-segmentation-using","title":"Long-tailed Instance Segmentation using Gumbel Optimized Loss","date":"2022-07-22","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/bridging-the-gap-between-object-and-image","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","date":"2022-07-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/open-vocabulary-object-detection-with","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","date":"2022-06-22","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":7,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/glipv2-unifying-localization-and-vision","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","date":"2022-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simple-open-vocabulary-object-detection-with","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","date":"2022-05-12","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/exploring-plain-vision-transformer-backbones","title":"Exploring Plain Vision Transformer Backbones for Object Detection","date":"2022-03-30","rows_on_this_dataset":4,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/detecting-twenty-thousand-classes-using-image","title":"Detecting Twenty-thousand Classes using Image-level Supervision","date":"2022-01-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/regionclip-region-based-language-image","title":"RegionCLIP: Region-based Language-Image Pretraining","date":"2021-12-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/grounded-language-image-pre-training","title":"Grounded Language-Image Pre-training","date":"2021-12-07","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lvis-challenge-track-technical-report-1st","title":"LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation","date":"2021-11-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-unified-objective-for-novel-class-discovery","title":"A Unified Objective for Novel Class Discovery","date":"2021-08-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-classification-equilibrium-in-long","title":"Exploring Classification Equilibrium in Long-Tailed Object Detection","date":"2021-08-17","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-shot-detection-via-vision-and-language","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","date":"2021-04-28","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/unsupervised-discovery-of-the-long-tail-in","title":"Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision","date":"2021-04-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/open-world-semi-supervised-learning-1","title":"Open-World Semi-Supervised Learning","date":"2021-02-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/equalization-loss-v2-a-new-gradient-balance","title":"Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection","date":"2020-12-15","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/simple-copy-paste-is-a-strong-data","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","date":"2020-12-13","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/1st-place-solution-of-lvis-challenge-2020-a","title":"1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask","date":"2020-09-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/forest-r-cnn-large-vocabulary-long-tailed","title":"Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation","date":"2020-08-13","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":29,"samples_harvested":169,"samples_ran":106,"samples_unverified":63,"pointer_only_for_licence":29,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}