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

Human Instance Segmentation On Ochuman

評価指標

AP

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
AP
Paper TitleRepository
CaSe18.0Count- and Similarity-aware R-CNN for Pedestrian Detection-
HQNet (ResNet-50)31.1You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
PolarMask + CIS23.4Real-time Human-Centric Segmentation for Complex Video Scenes-
BlendMask + CIS29.8Real-time Human-Centric Segmentation for Complex Video Scenes-
Crowd-SAM (ViT-L)31.4Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
JoPoSeg26.4PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation-
RTMDet-ins-l26.5Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
ExPoSeg26.8PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation-
Mask2Former27.8Object-Centric Multi-Task Learning for Human Instances-
HCQNet27.3Object-Centric Multi-Task Learning for Human Instances-
Mask RCNN16.9Count- and Similarity-aware R-CNN for Pedestrian Detection-
BaseNet-DPS25.5Object-Centric Multi-Task Learning for Human Instances-
ResNet-101-FPN + TTG v122.42Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation-
Pose2Seg23.8Pose2Seg: Detection Free Human Instance Segmentation
Mask2Former + Occlusion C&P28.3Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
BCNet20.6Occlusion-Aware Instance Segmentation via BiLayer Network Architectures
CondInst + CIS28.1Real-time Human-Centric Segmentation for Complex Video Scenes-
BBox-Mask-Pose 2x32.4Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
HQNet (ViT-L)38.8You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception
0 of 19 row(s) selected.