HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Pedestrian Detection On Citypersons

評価指標

Heavy MR^-2
Reasonable MR^-2
Small MR^-2
Test Time

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Heavy MR^-2
Reasonable MR^-2
Small MR^-2
Test Time
Paper TitleRepository
F2DNet (extra data)26.237.89.430.44s/imgF2DNet: Fast Focal Detection Network for Pedestrian Detection
Pedestron33.97.58.0-Generalizable Pedestrian Detection: The Elephant In The Room
FRCNN+Seg-14.822.6-CityPersons: A Diverse Dataset for Pedestrian Detection
TLL+MRF52.014.4--Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation-
FRCNN-15.425.6-CityPersons: A Diverse Dataset for Pedestrian Detection
TLL53.615.5--Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation-
LSFM31.98.58.80.18Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving-
ACSP + EuroCity Persons42.5---Adapted Center and Scale Prediction: More Stable and More Accurate
Beta R-CNN47.110.6--Beta R-CNN: Looking into Pedestrian Detection from Another Perspective-
NMS-Loss-10.08--NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection
DIW Loss28.376.237.36-Increasing pedestrian detection performance through weighting of detection impairing factors-
RepLoss56.913.2--Repulsion Loss: Detecting Pedestrians in a Crowd
FRCNN+FPN-Res50+refined feature map+Crowdhuman-10.67--CrowdHuman: A Benchmark for Detecting Human in a Crowd
F2DNet32.68.711.30.44s/imgF2DNet: Fast Focal Detection Network for Pedestrian Detection
ACSP46.39.3--Adapted Center and Scale Prediction: More Stable and More Accurate
LSFM (Additional Data)24.736.387.900.18Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving-
SOLIDER39.49.7--Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
CSP (with offset) + ResNet-5049.311.016.00.33s/imgCenter and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection
VLPD43.19.410.9-VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
ALFNet51.912.019.00.27Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting-
0 of 22 row(s) selected.