High-Resolution Representations for Labeling Pixels and Regions
read the original abstract
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. In this paper, we conduct a further study on high-resolution representations by introducing a simple yet effective modification and apply it to a wide range of vision tasks. We augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from the high-resolution convolution as done in~\cite{SunXLW19}. This simple modification leads to stronger representations, evidenced by superior results. We show top results in semantic segmentation on Cityscapes, LIP, and PASCAL Context, and facial landmark detection on AFLW, COFW, $300$W, and WFLW. In addition, we build a multi-level representation from the high-resolution representation and apply it to the Faster R-CNN object detection framework and the extended frameworks. The proposed approach achieves superior results to existing single-model networks on COCO object detection. The code and models have been publicly available at \url{https://github.com/HRNet}.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
CineMatte: Background Matting for Virtual Production and Beyond
CineMatte uses a cross-attention design on a Siamese DINOv3 ViT plus a pretrained upsampler to produce robust mattes for virtual production, backed by a new non-synthetic 4K VP dataset that supports camera motion.
-
Doppler Prompting for Stable mmWave-based Human Pose Estimation
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
-
PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training
PaCo-FR introduces a structured-masking and patch-codebook framework for unsupervised facial representation pre-training that claims state-of-the-art results on multiple facial tasks after training on only 2 million u...
-
From Virtual Environments to Real-World Trials: Emerging Trends in Autonomous Driving
A survey organizes synthetic data use, digital twin simulation, and domain adaptation techniques for autonomous driving while identifying open challenges like Sim2Real transfer.
-
Gesture-Aware Pretraining and Token Fusion for 3D Hand Pose Estimation
Gesture-aware pretraining on coarse and fine labels from InterHand2.6M improves 3D hand pose estimation accuracy over the EANet baseline when followed by per-joint token fusion.
-
Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios
MSAM with kernels 1-11 added to UNet skip connections yields 2.32% mIoU and 2.88% mF1 gains on hyperspectral urban driving datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.