paper-with-me

Human Instance Segmentation 벤치마크

Human Instance Segmentation on OCHuman

36개 결과 · ⬇ CSV · JSON

AP

20.6 23.55 26.5 29.45 32.4 2018-03 2026-11 Pose2Seg — 23.8 (2018-03-28) Pose2Seg — 23.8 (2018-03-28) ExPoSeg — 26.8 (2020-01-07) JoPoSeg — 26.4 (2020-01-07) ExPoSeg — 26.8 (2020-01-07) JoPoSeg — 26.4 (2020-01-07) BlendMask + CIS — 29.8 (2021-08-16) CondInst + CIS — 28.1 (2021-08-16) PolarMask + CIS — 23.4 (2021-08-16) BlendMask + CIS — 29.8 (2021-08-16) CondInst + CIS — 28.1 (2021-08-16) PolarMask + CIS — 23.4 (2021-08-16) BCNet — 20.6 (2022-08-08) BCNet — 20.6 (2022-08-08) Mask2Former + Occlusion C&P — 28.3 (2022-10-07) Mask2Former + Occlusion C&P — 28.3 (2022-10-07) ResNet-101-FPN + TTG v1 — 22.42 (2022-12-12) ResNet-101-FPN + TTG v1 — 22.42 (2022-12-12) Mask2Former — 27.8 (2023-03-13) HCQNet — 27.3 (2023-03-13) BaseNet-DPS — 25.5 (2023-03-13) Mask2Former — 27.8 (2023-03-13) HCQNet — 27.3 (2023-03-13) BaseNet-DPS — 25.5 (2023-03-13) HQNet (ResNet-50) — 31.1 (2023-12-09) HQNet (ResNet-50) — 31.1 (2023-12-09) Crowd-SAM (ViT-L) — 31.4 (2024-07-16) Crowd-SAM (ViT-L) — 31.4 (2024-07-16) BBox-Mask-Pose 2x — 32.4 (2024-12-02) RTMDet-ins-l — 26.5 (2024-12-02) BBox-Mask-Pose 2x — 32.4 (2024-12-02) RTMDet-ins-l — 26.5 (2024-12-02) Pose2Seg — 23.8 (2018-03-28) ExPoSeg — 26.8 (2020-01-07) BlendMask + CIS — 29.8 (2021-08-16) HQNet (ResNet-50) — 31.1 (2023-12-09) Crowd-SAM (ViT-L) — 31.4 (2024-07-16) BBox-Mask-Pose 2x — 32.4 (2024-12-02)
RankModel AP PaperCodeYear
1 BBox-Mask-Pose 2x 32.4 Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle MiraPurkrabek/BBoxMaskPose 2024
2 Crowd-SAM (ViT-L) 31.4 Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes felixcaae/crowdsam 2024
3 HQNet (ResNet-50) 31.1 You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception lishuhuai527/coco-unihuman 2023
4 BlendMask + CIS 29.8 Real-time Human-Centric Segmentation for Complex Video Scenes iigroup/hvisnet 2021
5 Mask2Former + Occlusion C&P 28.3 Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation levan92/occlusion-copy-paste 2022
6 CondInst + CIS 28.1 Real-time Human-Centric Segmentation for Complex Video Scenes iigroup/hvisnet 2021
7 Mask2Former 27.8 Object-Centric Multi-Task Learning for Human Instances 2023
8 HCQNet 27.3 Object-Centric Multi-Task Learning for Human Instances 2023
9 ExPoSeg 26.8 PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation 2020
10 RTMDet-ins-l 26.5 Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle MiraPurkrabek/BBoxMaskPose 2024
11 JoPoSeg 26.4 PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation 2020
12 BaseNet-DPS 25.5 Object-Centric Multi-Task Learning for Human Instances 2023
13 Pose2Seg 23.8 Pose2Seg: Detection Free Human Instance Segmentation open-mmlab/mmpose · liruilong940607/Pose2Seg · liruilong940607/OCHumanApi · +4 2018
14 PolarMask + CIS 23.4 Real-time Human-Centric Segmentation for Complex Video Scenes iigroup/hvisnet 2021
15 ResNet-101-FPN + TTG v1 22.42 Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation 2022
16 BCNet 20.6 Occlusion-Aware Instance Segmentation via BiLayer Network Architectures lkeab/BCNet 2022
17 CaSe 18.0 Count- and Similarity-aware R-CNN for Pedestrian Detection
18 Mask RCNN 16.9 Count- and Similarity-aware R-CNN for Pedestrian Detection
19 BBox-Mask-Pose 2x 32.4 Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle MiraPurkrabek/BBoxMaskPose 2024
20 Crowd-SAM (ViT-L) 31.4 Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes felixcaae/crowdsam 2024
1–20 / 36 다음 → 페이지당 10 20 50 100