High-Resolution Representations for Labeling Pixels and Regions

Ke SunYang ZhaoBorui JiangTianheng ChengBin XiaoDong LiuYadong MuXinggang WangWenyu LiuJingdong Wang

   Papers with code   Abstract  PDF

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{SunXLW19}, recently developed for human pose estimation, maintains high-resolution representations through the whole process by connecting high-to-low resolution convolutions in \emph{parallel} and produces strong high-resolution representations by repeatedly conducting fusions across parallel convolutions... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
HTC
(HRNetV2p-W32)
0.453
--
2
Mask R-CNN
(HRNetV2p-W32, cascade)
0.445
--
3
Cascade R-CNN
(HRNetV2p-W32)
0.436
--
4
Mask R-CNN
(HRNetV2p-W32)
0.417
--
5
Mask R-CNN
(HRNetV2p-W32, 1x LR)
0.407
0.409
6
Faster R-CNN
(HRNetV2p-W32)
0.406
--
7
Faster R-CNN
(HRNetV2p-W32, 1x LR)
0.395
0.396
8
Mask R-CNN
(HRNetV2p-W18)
0.392
--
9
Faster R-CNN
(HRNetV2p-W18)
0.383
--
10
Mask R-CNN
(HRNetV2p-W18, 1x LR)
0.372
0.371
11
Faster R-CNN
(HRNetV2p-W18, 1x LR)
0.361
0.362