Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Human Instance Segmentation On Ochuman

Metriken

AP

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	AP	Paper Title	Repository
CaSe	18.0	Count- and Similarity-aware R-CNN for Pedestrian Detection	-
HQNet (ResNet-50)	31.1	You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
PolarMask + CIS	23.4	Real-time Human-Centric Segmentation for Complex Video Scenes	-
BlendMask + CIS	29.8	Real-time Human-Centric Segmentation for Complex Video Scenes	-
Crowd-SAM (ViT-L)	31.4	Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
JoPoSeg	26.4	PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation	-
RTMDet-ins-l	26.5	Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
ExPoSeg	26.8	PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation	-
Mask2Former	27.8	Object-Centric Multi-Task Learning for Human Instances	-
HCQNet	27.3	Object-Centric Multi-Task Learning for Human Instances	-
Mask RCNN	16.9	Count- and Similarity-aware R-CNN for Pedestrian Detection	-
BaseNet-DPS	25.5	Object-Centric Multi-Task Learning for Human Instances	-
ResNet-101-FPN + TTG v1	22.42	Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation	-
Pose2Seg	23.8	Pose2Seg: Detection Free Human Instance Segmentation
Mask2Former + Occlusion C&P	28.3	Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
BCNet	20.6	Occlusion-Aware Instance Segmentation via BiLayer Network Architectures
CondInst + CIS	28.1	Real-time Human-Centric Segmentation for Complex Video Scenes	-
BBox-Mask-Pose 2x	32.4	Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
HQNet (ViT-L)	38.8	You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

0 of 19 row(s) selected.