{"url":"/task/2d-object-detection","name":"2D Object Detection","slug":"2d-object-detection","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":210,"papers_with_code":118,"benchmarks":21,"benchmark_tables_in_archive":21,"benchmark_tables_shown":21,"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":92,"subtasks":15,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/2d-object-detection-on-sardet-100k","slug":"2d-object-detection-on-sardet-100k","dataset":"SARDet-100K","dataset_url":"/dataset/sardet-100k","rows_in_archive":13,"metrics":["box mAP","mAP","mAP@50","mAP@75"],"first_row_in_archive_order":{"model":"DenoDet","paper_title":"DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images","paper_url":"/paper/denodet-attention-as-deformable-multi","paper_date":"2024-06-05","arxiv_id":"2406.02833","code_links":[{"title":"zcablii/sardet_100k","url":"https://github.com/zcablii/sardet_100k"},{"title":"grokcv/groksar","url":"https://github.com/grokcv/groksar"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-dronevehicle","slug":"2d-object-detection-on-dronevehicle","dataset":"DroneVehicle","dataset_url":"/dataset/dronevehicle","rows_in_archive":11,"metrics":["test/mAP50","test/mAP","Val/mAP50"],"first_row_in_archive_order":{"model":"OAFA","paper_title":"Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection","paper_url":"/paper/weakly-misalignment-free-adaptive-feature","paper_date":"2024-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-ceymo","slug":"2d-object-detection-on-ceymo","dataset":"CeyMo","dataset_url":"/dataset/ceymo","rows_in_archive":5,"metrics":["mAP"],"first_row_in_archive_order":{"model":"TransMind","paper_title":"Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation","paper_url":"/paper/open-transmind-a-new-baseline-and-benchmark","paper_date":"2023-04-12","arxiv_id":"2304.06051","code_links":[{"title":"Traffic-X/Open-TransMind","url":"https://github.com/Traffic-X/Open-TransMind"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-txl-pbc-a-freely","slug":"2d-object-detection-on-txl-pbc-a-freely","dataset":"TXL-PBC: a freely accessible labeled peripheral blood cell dataset","dataset_url":null,"rows_in_archive":5,"metrics":["mAP50"],"first_row_in_archive_order":{"model":"yolov5n","paper_title":"TXL-PBC: a freely accessible labeled peripheral blood cell dataset","paper_url":"/paper/txl-pbc-a-freely-accessible-labeled","paper_date":"2024-07-18","arxiv_id":"2407.13214","code_links":[{"title":"lugan113/TXL-PBC_Dataset","url":"https://github.com/lugan113/TXL-PBC_Dataset"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-exdark","slug":"2d-object-detection-on-exdark","dataset":"ExDark","dataset_url":"/dataset/exdark","rows_in_archive":3,"metrics":["mAP"],"first_row_in_archive_order":{"model":"EMV-YOLO","paper_title":"Toward Highly Efficient Semantic-Guided Machine Vision for Low-Light Object Detection","paper_url":"/paper/toward-highly-efficient-semantic-guided","paper_date":"2024-12-20","arxiv_id":null,"code_links":[{"title":"Zeng555/EMV-YOLO","url":"https://github.com/Zeng555/EMV-YOLO"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-scoraldet-dataset-1","slug":"2d-object-detection-on-scoraldet-dataset-1","dataset":"SCoralDet Dataset","dataset_url":"/dataset/scoraldet-dataset-1","rows_in_archive":3,"metrics":["mAP50","mAP"],"first_row_in_archive_order":{"model":"MambaCoral-DiffDet","paper_title":"A Diffusion Model and Knowledge Distillation Framework for Robust Coral Detection in Complex Underwater Environments","paper_url":"/paper/a-diffusion-model-and-knowledge-distillation","paper_date":"2025-01-06","arxiv_id":null,"code_links":[{"title":"RDXiaoLu/MambaCoral-DiffDet","url":"https://github.com/RDXiaoLu/MambaCoral-DiffDet"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-clear-weather","slug":"2d-object-detection-on-clear-weather","dataset":"Clear Weather","dataset_url":"/dataset/clear-weather","rows_in_archive":2,"metrics":["clear hard (AP)"],"first_row_in_archive_order":{"model":"HRFuser-T","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_url":"/paper/hrfuser-a-multi-resolution-sensor-fusion","paper_date":"2022-06-30","arxiv_id":"2206.15157","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-dense-fog","slug":"2d-object-detection-on-dense-fog","dataset":"Dense Fog","dataset_url":"/dataset/stf","rows_in_archive":2,"metrics":["dense fog hard (AP)","light fog hard (AP)","snow/rain hard (AP)"],"first_row_in_archive_order":{"model":"HRFuser-T","paper_title":"HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection","paper_url":"/paper/hrfuser-a-multi-resolution-sensor-fusion","paper_date":"2022-06-30","arxiv_id":"2206.15157","code_links":[{"title":"timbroed/hrfuser","url":"https://github.com/timbroed/hrfuser"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-radiate","slug":"2d-object-detection-on-radiate","dataset":"RADIATE","dataset_url":"/dataset/radiate","rows_in_archive":2,"metrics":["mAP@0.3"],"first_row_in_archive_order":{"model":"SIRA","paper_title":"SIRA: Scalable Inter-frame Relation and Association for Radar Perception","paper_url":"/paper/sira-scalable-inter-frame-relation-and-1","paper_date":"2024-11-04","arxiv_id":"2411.02220","code_links":[],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-1","slug":"2d-object-detection-on-1","dataset":null,"dataset_url":null,"rows_in_archive":1,"metrics":[],"first_row_in_archive_order":{"model":null,"paper_title":"PP-YOLOE: An evolved version of YOLO","paper_url":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_date":"2022-03-30","arxiv_id":"2203.16250","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"Nioolek/PPYOLOE_pytorch","url":"https://github.com/Nioolek/PPYOLOE_pytorch"},{"title":"Gaurav14cs17/YOLOE","url":"https://github.com/Gaurav14cs17/YOLOE"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/YOLOv5"},{"title":"Mind23-2/MindCode-130","url":"https://github.com/Mind23-2/MindCode-130"}],"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}}},{"leaderboard":"/sota/2d-object-detection-on-bdd100k-val","slug":"2d-object-detection-on-bdd100k-val","dataset":"BDD100K val","dataset_url":"/dataset/bdd100k","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"InternImage-H","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_url":"/paper/internimage-exploring-large-scale-vision","paper_date":"2022-11-10","arxiv_id":"2211.05778","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/2d-object-detection-on-clcxray","slug":"2d-object-detection-on-clcxray","dataset":"CLCXray","dataset_url":"/dataset/clcxray","rows_in_archive":1,"metrics":["Detection: Full (mAP@0.5)"],"first_row_in_archive_order":{"model":"LACLS","paper_title":"Detecting Overlapping Objects in X-ray Security Imagery by a Label-aware Mechanism","paper_url":"/paper/detecting-overlapping-objects-in-x-ray","paper_date":"2022-02-28","arxiv_id":null,"code_links":[{"title":"greysonphoenix/clcxray","url":"https://github.com/greysonphoenix/clcxray"},{"title":"Vill-Lab/2022-TIFS-CLCXray","url":"https://github.com/Vill-Lab/2022-TIFS-CLCXray"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-duo","slug":"2d-object-detection-on-duo","dataset":"DUO","dataset_url":"/dataset/duo","rows_in_archive":1,"metrics":["All mAP","AP50","AP75"],"first_row_in_archive_order":{"model":"GCC-Net","paper_title":"A Gated Cross-domain Collaborative Network for Underwater Object Detection","paper_url":"/paper/a-gated-cross-domain-collaborative-network","paper_date":"2023-06-25","arxiv_id":"2306.14141","code_links":[{"title":"ixiaohuihuihui/gcc-net","url":"https://github.com/ixiaohuihuihui/gcc-net"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-etdii-dataset","slug":"2d-object-detection-on-etdii-dataset","dataset":"ETDII Dataset","dataset_url":"/dataset/etdii-dataset","rows_in_archive":1,"metrics":["mAP@0.5"],"first_row_in_archive_order":{"model":"SCAResNet","paper_title":"SCAResNet: A ResNet Variant Optimized for Tiny Object Detection in Transmission and Distribution Towers","paper_url":"/paper/scaresnet-a-resnet-variant-optimized-for-tiny","paper_date":"2024-04-05","arxiv_id":"2404.04179","code_links":[{"title":"lisavilalee/scaresnet_mmdet","url":"https://github.com/lisavilalee/scaresnet_mmdet"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-fisheye8k","slug":"2d-object-detection-on-fisheye8k","dataset":"FishEye8K","dataset_url":"/dataset/fisheye8k","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Yolov8x (640x640)","paper_title":"FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection","paper_url":"/paper/fisheye8k-a-benchmark-and-dataset-for-fisheye","paper_date":"2023-05-27","arxiv_id":"2305.17449","code_links":[{"title":"moyog/fisheye8k","url":"https://github.com/moyog/fisheye8k"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-radiogalaxynet-dataset","slug":"2d-object-detection-on-radiogalaxynet-dataset","dataset":"RadioGalaxyNET Dataset","dataset_url":"/dataset/radiogalaxynet-dataset","rows_in_archive":1,"metrics":["COCO-style AP"],"first_row_in_archive_order":{"model":"Gal-DINO","paper_title":"RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts","paper_url":"/paper/radiogalaxynet-dataset-and-novel-computer","paper_date":"2023-12-01","arxiv_id":"2312.00306","code_links":[{"title":"nikhel1/gal-detr","url":"https://github.com/nikhel1/gal-detr"},{"title":"nikhel1/gal-deformable-detr","url":"https://github.com/nikhel1/gal-deformable-detr"},{"title":"nikhel1/gal-dino","url":"https://github.com/nikhel1/gal-dino"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-rf100","slug":"2d-object-detection-on-rf100","dataset":"RF100","dataset_url":"/dataset/rf100","rows_in_archive":1,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"GLIP","paper_title":"Grounded Language-Image Pre-training","paper_url":"/paper/grounded-language-image-pre-training","paper_date":"2021-12-07","arxiv_id":"2112.03857","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"brown-palm/ObjectPrompt","url":"https://github.com/brown-palm/ObjectPrompt"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/2d-object-detection-on-rtts","slug":"2d-object-detection-on-rtts","dataset":"RTTS","dataset_url":null,"rows_in_archive":1,"metrics":["MAP"],"first_row_in_archive_order":{"model":"WARLearn","paper_title":"WARLearn: Weather-Adaptive Representation Learning","paper_url":"/paper/warlearn-weather-adaptive-representation","paper_date":"2024-11-21","arxiv_id":"2411.14095","code_links":[{"title":"shubhamagarwal12/warlearn","url":"https://github.com/shubhamagarwal12/warlearn"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-trr360d","slug":"2d-object-detection-on-trr360d","dataset":"TRR360D","dataset_url":"/dataset/trr360d","rows_in_archive":1,"metrics":["AP50(T<90)","AP90(T<90)"],"first_row_in_archive_order":{"model":"rotated-retinanet-rbox-r360_r50_fpn_6x.py","paper_title":"TRR360D: A dataset for 360 degree rotated rectangular box table detection","paper_url":"/paper/t360rrd-a-dataset-for-360-degree-rotated","paper_date":"2023-03-03","arxiv_id":"2303.01894","code_links":[],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-uav-pdd2023","slug":"2d-object-detection-on-uav-pdd2023","dataset":"UAV-PDD2023","dataset_url":"/dataset/uav-pdd2023","rows_in_archive":1,"metrics":["AP@0.5"],"first_row_in_archive_order":{"model":"RT-DSAFDet","paper_title":"Real-Time Dynamic Scale-Aware Fusion Detection Network: Take Road Damage Detection as an example","paper_url":"/paper/real-time-dynamic-scale-aware-fusion","paper_date":"2024-09-04","arxiv_id":"2409.02546","code_links":[{"title":"JEFfersusu/RT-DSAFDet","url":"https://github.com/JEFfersusu/RT-DSAFDet"}],"syntology":null}},{"leaderboard":"/sota/2d-object-detection-on-uavdb","slug":"2d-object-detection-on-uavdb","dataset":"UAVDB","dataset_url":"/dataset/uavdb","rows_in_archive":1,"metrics":["AP50"],"first_row_in_archive_order":{"model":"YOLOv12x","paper_title":"UAVDB: Trajectory-Guided Adaptable Bounding Boxes for UAV Detection","paper_url":"/paper/uavdb-trajectory-guided-adaptable-bounding","paper_date":"2024-09-09","arxiv_id":"2409.06490","code_links":[{"title":"wish44165/uavdb","url":"https://github.com/wish44165/uavdb"}],"syntology":null}}],"datasets":[{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/hypersim","name":"Hypersim","full_name":"","num_papers_in_archive":108},{"url":"/dataset/exdark","name":"ExDark","full_name":"Exclusively Dark Image Dataset","num_papers_in_archive":58},{"url":"/dataset/coco-o","name":"COCO-O","full_name":"","num_papers_in_archive":44},{"url":"/dataset/clear-weather","name":"Clear Weather","full_name":"DENSE","num_papers_in_archive":34},{"url":"/dataset/paco","name":"PACO","full_name":"Parts and Attributes of Common Objects","num_papers_in_archive":32},{"url":"/dataset/kitti-mots","name":"KITTI MOTS","full_name":"KITTI Multi-Object Tracking and Segmentation (MOTS) Evaluation","num_papers_in_archive":28},{"url":"/dataset/flickrlogos-32","name":"FlickrLogos-32","full_name":"","num_papers_in_archive":26},{"url":"/dataset/radiate","name":"RADIATE","full_name":"RAdar Dataset In Adverse weaThEr","num_papers_in_archive":24},{"url":"/dataset/stf","name":"Dense Fog","full_name":"DENSE","num_papers_in_archive":20},{"url":"/dataset/coir","name":"CoIR","full_name":"Code Information Retrieval Benchmark","num_papers_in_archive":18},{"url":"/dataset/dronevehicle","name":"DroneVehicle","full_name":"VisDrone-DroneVehicle","num_papers_in_archive":18},{"url":"/dataset/gen1-detection","name":"GEN1 Detection","full_name":"Prophesee GEN1 Automotive Detection Dataset","num_papers_in_archive":13},{"url":"/dataset/sardet-100k","name":"SARDet-100K","full_name":"","num_papers_in_archive":13},{"url":"/dataset/2024-ai-city-challenge-mtmc-people-tracking","name":"2024 AI City Challenge","full_name":"","num_papers_in_archive":10},{"url":"/dataset/uiis-dataset","name":"UIIS","full_name":"General Underwater Image Instance Segmentation dataset","num_papers_in_archive":9},{"url":"/dataset/duo","name":"DUO","full_name":"Detecting Underwater Objects","num_papers_in_archive":8},{"url":"/dataset/dolphins","name":"DOLPHINS","full_name":"Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving","num_papers_in_archive":7},{"url":"/dataset/ceymo","name":"CeyMo","full_name":"","num_papers_in_archive":6},{"url":"/dataset/open-images-v7","name":"Open Images V7","full_name":"","num_papers_in_archive":6},{"url":"/dataset/vedai","name":"VEDAI","full_name":"Vehicle Detection in Aerial Imagery","num_papers_in_archive":6},{"url":"/dataset/fisheye8k","name":"FishEye8K","full_name":"FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection","num_papers_in_archive":5},{"url":"/dataset/rf100","name":"RF100","full_name":"Roboflow 100","num_papers_in_archive":5},{"url":"/dataset/soda-d","name":"SODA-D","full_name":"","num_papers_in_archive":5},{"url":"/dataset/fes","name":"FES","full_name":"Fisheye Evaluation Suite","num_papers_in_archive":4},{"url":"/dataset/usis10k","name":"USIS10K","full_name":"Large-scale Underwater Salient Instance Segmentation Dataset","num_papers_in_archive":4},{"url":"/dataset/br35h-brain-tumor-detection-2020","name":"Br35H :: Brain Tumor Detection 2020","full_name":"Br35H :: Brain Tumor Detection 2020","num_papers_in_archive":3},{"url":"/dataset/mosquitofusion","name":"MosquitoFusion","full_name":"","num_papers_in_archive":3},{"url":"/dataset/popart","name":"PoPArt","full_name":"Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History","num_papers_in_archive":3},{"url":"/dataset/scoraldet-dataset-1","name":"SCoralDet Dataset","full_name":"Soft-Coral Detection Dataset","num_papers_in_archive":3},{"url":"/dataset/aria-digital-twin-dataset","name":"Aria Digital Twin Dataset","full_name":"Aria Digital Twin Dataset","num_papers_in_archive":2},{"url":"/dataset/c2a-dataset-human-detection-in-disaster","name":"C2A: Human Detection in Disaster Scenarios","full_name":"Combination to Application","num_papers_in_archive":2},{"url":"/dataset/cvb-a-video-dataset-of-cattle-visual","name":"CVB","full_name":"Video Dataset of Cattle Visual Behaviors","num_papers_in_archive":2},{"url":"/dataset/destruction","name":"destruction","full_name":"desctruction detection dataset","num_papers_in_archive":2},{"url":"/dataset/lote-animal","name":"LoTE-Animal","full_name":"LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding","num_papers_in_archive":2},{"url":"/dataset/mmvr","name":"MMVR","full_name":"Millimeter-wave Multi-View Radar (MMVR) Dataset","num_papers_in_archive":2},{"url":"/dataset/parcel3d","name":"Parcel3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/tbbr","name":"TBBR","full_name":"Thermal Bridges on Building Rooftops","num_papers_in_archive":2},{"url":"/dataset/a-collection-of-131-ct-datasets-of-pieces-of","name":"A collection of 131 CT datasets of pieces of modeling clay containing stones","full_name":"","num_papers_in_archive":1},{"url":"/dataset/a-collection-of-x-ray-projections-of-131","name":"A collection of X-ray projections of 131 pieces of modeling clay containing stones for machine learning-driven object detection","full_name":"","num_papers_in_archive":1},{"url":"/dataset/a-large-scale-fish-dataset","name":"A Large Scale Fish Dataset","full_name":"A Large-Scale Dataset for Fish Segmentation and Classification","num_papers_in_archive":1},{"url":"/dataset/blood-cell-detection-dataset","name":"Blood Cell Detection Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bramble-flower-image-dataset","name":"Bramble flower image dataset","full_name":"BRAMBLE FLOWER DETECTION AND CLASSIFICATION DATASET FOR PRECISION POLLINATION","num_papers_in_archive":1},{"url":"/dataset/chessred2k","name":"ChessReD2K","full_name":"Chess Recognition Dataset 2K","num_papers_in_archive":1},{"url":"/dataset/clcxray","name":"CLCXray","full_name":"Cutters and Liquid Containers X-ray Dataset","num_papers_in_archive":1},{"url":"/dataset/coco-ooc","name":"COCO-OOC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cy101-dataset","name":"CY101 Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dermsynth3d","name":"DermSynth3D","full_name":"3DBodyTex.DermSynth3D","num_papers_in_archive":1},{"url":"/dataset/egc-fphfs","name":"EGC-FPHFS","full_name":"Early Gastric Cancer Data from First People's Hospital of Foshan","num_papers_in_archive":1},{"url":"/dataset/ego-ch-gaze","name":"EGO-CH-Gaze","full_name":"Learning to Detect Attended Objects in Cultural Sites with Gaze Signals and Weak Object Supervision","num_papers_in_archive":1},{"url":"/dataset/elethermal","name":"EleThermal","full_name":"EleThermal: Infrared Elephant Images Dataset","num_papers_in_archive":1},{"url":"/dataset/enseg","name":"ENSeg","full_name":"","num_papers_in_archive":1},{"url":"/dataset/essvp","name":"ESSVP","full_name":"ESSVP dataset","num_papers_in_archive":1},{"url":"/dataset/etdii-dataset","name":"ETDII Dataset","full_name":"Electric Transmission and Distribution Infrastructure Imagery Dataset","num_papers_in_archive":1},{"url":"/dataset/fathomnet2023","name":"FathomNet2023","full_name":"FathomNet2023 Competition Dataset","num_papers_in_archive":1},{"url":"/dataset/highwaypavementcrackdetection","name":"HighwayPavementCrackDetection","full_name":"","num_papers_in_archive":1},{"url":"/dataset/hrplanesv2","name":"HRPlanesV2","full_name":"HRPlanesv2 - High Resolution Satellite Imagery for Aircraft Detection","num_papers_in_archive":1},{"url":"/dataset/infraparis","name":"InfraParis","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kitchen-items-in-ai2-thor","name":"Kitchen Items in AI2-THOR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mars-sample-localization","name":"Mars Sample Localization","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mp-idb","name":"MP-IDB","full_name":"MP-IDB: The Malaria Parasite Image Database for Image Processing and Analysis","num_papers_in_archive":1},{"url":"/dataset/mvtec-fs","name":"MVTec-FS","full_name":"MVTec few-shot detection and classfication dataset","num_papers_in_archive":1},{"url":"/dataset/nih-3t3-microtubule-cell-dataset","name":"NIH 3T3 microtubule cell dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nii-cu-mapd","name":"NII-CU MAPD","full_name":"NII-CU Multispectral Aerial Person Detection Dataset","num_papers_in_archive":1},{"url":"/dataset/peripheral-blood-cell","name":"Peripheral Blood Cell","full_name":"","num_papers_in_archive":1},{"url":"/dataset/radiogalaxynet-dataset","name":"RadioGalaxyNET Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/simbev","name":"SimBEV","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sjtu-multispectral-object-detection-smod","name":"SJTU Multispectral Object Detection (SMOD) Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tao-amodal","name":"TAO-Amodal","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tirod","name":"TiROD","full_name":"Tiny Robotics Object Detection","num_papers_in_archive":1},{"url":"/dataset/trr360d","name":"TRR360D","full_name":"TRR360D","num_papers_in_archive":1},{"url":"/dataset/txl-pbc-dataset","name":"TXL-PBC dataset","full_name":"a freely accessible labeled peripheral blood cell dataset","num_papers_in_archive":1},{"url":"/dataset/uav-pdd2023","name":"UAV-PDD2023","full_name":"","num_papers_in_archive":1},{"url":"/dataset/uavdb","name":"UAVDB","full_name":"Trajectory-Guided Adaptable Bounding Boxes for UAV Detection","num_papers_in_archive":1},{"url":"/dataset/applebbch76","name":"AppleBBCH76","full_name":"Apple Fruitlets BBCH76-78","num_papers_in_archive":0},{"url":"/dataset/applebbch81","name":"AppleBBCH81","full_name":"Apple Fruits BBCH 81-85","num_papers_in_archive":0},{"url":"/dataset/bone-fracture-multi-region-x-ray-data","name":"Bone Fracture Multi-Region X-ray Data","full_name":"","num_papers_in_archive":0},{"url":"/dataset/bone-fracture-multi-region-x-ray-dataset","name":"Bone Fracture Multi-Region X-ray Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/car-crash-dataset-russia-2022-2023","name":"Car crash dataset RUSSIA 2022-2023","full_name":"","num_papers_in_archive":0},{"url":"/dataset/car-datasets-in-multiple-scenes","name":"Car datasets in multiple scenes","full_name":"","num_papers_in_archive":0},{"url":"/dataset/cherrybbch72","name":"CherryBBCH72","full_name":"Cherry fruitlets BBCH72","num_papers_in_archive":0},{"url":"/dataset/cherrybbch81","name":"CherryBBCH81","full_name":"Cherry Fruits","num_papers_in_archive":0},{"url":"/dataset/codrone","name":"CODrone","full_name":"","num_papers_in_archive":0},{"url":"/dataset/construction-vehicle-image-dataset-trucks","name":"Construction Vehicle Image Dataset |Trucks|Tractor etc.","full_name":"","num_papers_in_archive":0},{"url":"/dataset/scoraldet-dataset","name":"Coral test","full_name":"test","num_papers_in_archive":0},{"url":"/dataset/fei","name":"fish","full_name":"fishway","num_papers_in_archive":0},{"url":"/dataset/infinity-spills-basic-dataset","name":"Infinity Spills Basic Dataset","full_name":"Infinity Spills Basic Dataset","num_papers_in_archive":0},{"url":"/dataset/multi-spectral-leaf-segmentation","name":"Multi-Spectral Leaf Segmentation","full_name":"Multi-Spectral Leaf Segmentation For Crop/Weed Identification","num_papers_in_archive":0},{"url":"/dataset/ntlnp-wildlife-image-dataset","name":"NTLNP","full_name":"wildlife image dataset","num_papers_in_archive":0},{"url":"/dataset/osdd","name":"OSDD","full_name":"Object State Detection Dataset","num_papers_in_archive":0},{"url":"/dataset/pear640","name":"Pear640","full_name":"","num_papers_in_archive":0},{"url":"/dataset/pfruitlet640","name":"PFruitlet640","full_name":"PearFruitlet640","num_papers_in_archive":0}],"subtasks":[{"url":"/task/2d-cyclist-detection","name":"2D Cyclist Detection"},{"url":"/task/2d-tiny-object-detection","name":"2D Tiny Object Detection"},{"url":"/task/drivable-area-detection","name":"Drivable Area Detection"},{"url":"/task/edge-detection","name":"Edge Detection"},{"url":"/task/gui-element-detection","name":"GUI Element Detection"},{"url":"/task/hand-detection","name":"Hand Detection"},{"url":"/task/intention-oriented-object-detection","name":"Intention-oriented Object Detection"},{"url":"/task/long-tailed-object-detection","name":"Long-tailed Object Detection"},{"url":"/task/medical-image-detection","name":"medical image detection"},{"url":"/task/novel-object-detection","name":"Novel Object Detection"},{"url":"/task/object-detection","name":"Object Detection"},{"url":"/task/sar-ship-detection","name":"SAR Ship Detection"},{"url":"/task/semi-supervised-object-detection","name":"Semi-Supervised Object Detection"},{"url":"/task/thermal-image-segmentation","name":"Thermal Image Segmentation"},{"url":"/task/vessel-detection","name":"Vessel Detection"}],"parent_tasks":[],"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":30,"of":118,"tagged_in_all":210,"items":[{"url":"/paper/focal-loss-for-dense-object-detection","title":"Focal Loss for Dense Object Detection","date":"2017-08-07","arxiv_id":"1708.02002","repositories_listed":234,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/faster-r-cnn-towards-real-time-object","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","date":"2015-06-04","arxiv_id":"1506.01497","repositories_listed":196,"syntology":{"n":124,"n_ran":59,"n_unverified":65,"n_pointer_only":42}},{"url":"/paper/fcos-fully-convolutional-one-stage-object","title":"FCOS: Fully Convolutional One-Stage Object Detection","date":"2019-04-02","arxiv_id":"1904.01355","repositories_listed":87,"syntology":{"n":40,"n_ran":13,"n_unverified":27,"n_pointer_only":18}},{"url":"/paper/yolox-exceeding-yolo-series-in-2021","title":"YOLOX: Exceeding YOLO Series in 2021","date":"2021-07-18","arxiv_id":"2107.08430","repositories_listed":42,"syntology":{"n":23,"n_ran":1,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/scaled-yolov4-scaling-cross-stage-partial","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","date":"2020-11-16","arxiv_id":"2011.08036","repositories_listed":41,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","arxiv_id":"2005.12872","repositories_listed":37,"syntology":{"n":92,"n_ran":59,"n_unverified":33,"n_pointer_only":19}},{"url":"/paper/yolov7-trainable-bag-of-freebies-sets-new","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","date":"2022-07-06","arxiv_id":"2207.02696","repositories_listed":21,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","arxiv_id":"2010.04159","repositories_listed":20,"syntology":{"n":55,"n_ran":29,"n_unverified":26,"n_pointer_only":21}},{"url":"/paper/detrs-beat-yolos-on-real-time-object","title":"DETRs Beat YOLOs on Real-time Object Detection","date":"2023-04-17","arxiv_id":"2304.08069","repositories_listed":9,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/pp-yoloe-an-evolved-version-of-yolo","title":"PP-YOLOE: An evolved version of YOLO","date":"2022-03-30","arxiv_id":"2203.16250","repositories_listed":8,"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/dab-detr-dynamic-anchor-boxes-are-better-1","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","date":"2022-01-28","arxiv_id":"2201.12329","repositories_listed":8,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/cascade-r-cnn-delving-into-high-quality","title":"Cascade R-CNN: Delving into High Quality Object Detection","date":"2017-12-03","arxiv_id":"1712.00726","repositories_listed":8,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/tood-task-aligned-one-stage-object-detection","title":"TOOD: Task-aligned One-stage Object Detection","date":"2021-08-17","arxiv_id":"2108.07755","repositories_listed":6,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/sparse-r-cnn-end-to-end-object-detection-with","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","date":"2020-11-25","arxiv_id":"2011.12450","repositories_listed":6,"syntology":null},{"url":"/paper/detection-of-accounting-anomalies-in-the","title":"Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks","date":"2019-08-02","arxiv_id":"1908.00734","repositories_listed":4,"syntology":null},{"url":"/paper/visionreasoner-unified-visual-perception-and","title":"VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning","date":"2025-05-17","arxiv_id":"2505.12081","repositories_listed":3,"syntology":{"n":15,"n_ran":1,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/yolov10-real-time-end-to-end-object-detection","title":"YOLOv10: Real-Time End-to-End Object Detection","date":"2024-05-23","arxiv_id":"2405.14458","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/saratr-x-a-foundation-model-for-synthetic","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","date":"2024-05-15","arxiv_id":"2405.09365","repositories_listed":3,"syntology":null},{"url":"/paper/salience-detr-enhancing-detection-transformer-1","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","date":"2024-03-24","arxiv_id":"2403.16131","repositories_listed":3,"syntology":{"n":23,"n_ran":11,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/radiogalaxynet-dataset-and-novel-computer","title":"RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts","date":"2023-12-01","arxiv_id":"2312.00306","repositories_listed":3,"syntology":null},{"url":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","arxiv_id":"2211.05778","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/small-object-detection-via-pixel-level","title":"Small Object Detection via Pixel Level Balancing With Applications to Blood Cell Detection","date":"2022-06-17","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/grounded-language-image-pre-training","title":"Grounded Language-Image Pre-training","date":"2021-12-07","arxiv_id":"2112.03857","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/efficientpose-an-efficient-accurate-and","title":"EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach","date":"2020-11-09","arxiv_id":"2011.04307","repositories_listed":3,"syntology":null},{"url":"/paper/relation-detr-exploring-explicit-position","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","date":"2024-07-16","arxiv_id":"2407.11699","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/denodet-attention-as-deformable-multi","title":"DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images","date":"2024-06-05","arxiv_id":"2406.02833","repositories_listed":2,"syntology":null},{"url":"/paper/openagents-an-open-platform-for-language","title":"OpenAgents: An Open Platform for Language Agents in the Wild","date":"2023-10-16","arxiv_id":"2310.10634","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mathbf-c-2-former-calibrated-and","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","date":"2023-06-28","arxiv_id":"2306.16175","repositories_listed":2,"syntology":null},{"url":"/paper/2d-object-detection-with-transformers-a","title":"Object Detection with Transformers: A Review","date":"2023-06-07","arxiv_id":"2306.04670","repositories_listed":2,"syntology":null},{"url":"/paper/designing-bert-for-convolutional-networks","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","date":"2023-01-09","arxiv_id":"2301.03580","repositories_listed":2,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":0}}],"syntology_records":21,"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"}}