Pedestrian Detection On Caltech

Metriken

Reasonable Miss Rate

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Reasonable Miss Rate	Paper Title	Repository
FRCNN+FPN-Res50+refined feature map+Crowdhuman	3.46	CrowdHuman: A Benchmark for Detecting Human in a Crowd	-
OR-CNN + CityPersons dataset	4.1	Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd	-
ALFNet	6.1	Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting	-
F2DNet (extra data)	1.71	F2DNet: Fast Focal Detection Network for Pedestrian Detection	-
NNNF	16.20	Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry	-
MS-CNN	9.95	A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection	-
CSP + CityPersons dataset	3.8	Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection	-
F-DNN+SS	8.18	Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection	-
Zhang et al. *	5.1	CityPersons: A Diverse Dataset for Pedestrian Detection	-
RepLoss + CityPersons dataset	4.0	Repulsion Loss: Detecting Pedestrians in a Crowd	-
RepLoss	5.0	Repulsion Loss: Detecting Pedestrians in a Crowd	-
TA-CNN	20.9	Pedestrian Detection aided by Deep Learning Semantic Tasks	-
F2DNet	2.2	F2DNet: Fast Focal Detection Network for Pedestrian Detection	-
LDCF	24.8	Local Decorrelation For Improved Pedestrian Detection	-
AlexNet	23.3	Taking a Deeper Look at Pedestrians	-
FasterRCNN	8.7	Is Faster R-CNN Doing Well for Pedestrian Detection?	-
Zhang et al.	5.8	CityPersons: A Diverse Dataset for Pedestrian Detection	-
Part-level CNN + saliency and bounding box alignment	12.4	Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment	-
RPN+BF	7.3	Is Faster R-CNN Doing Well for Pedestrian Detection?	-
NMS-Loss	2.92	NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection	-

0 of 33 row(s) selected.