Deep High-Resolution Representation Learning for Visual Recognition (2019-08-20T00:00:00.000000Z)

TL;DR

The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.

Abstract

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet.

Authors

Ke Sun

6 papers

Bin Xiao

6 papers

Jingdong Wang

10 papers

TL;DR

Abstract

Authors

References197 items

Object Detection

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

VisDrone-VID2019: The Vision Meets Drone Object Detection in Video Challenge Results

VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results

Object-Contextual Representations for Semantic Segmentation

Asymmetric Non-Local Neural Networks for Semantic Segmentation

Interlaced Sparse Self-Attention for Semantic Segmentation

Progressive Image Inpainting with Full-Resolution Residual Network

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

MMDetection: Open MMLab Detection Toolbox and Benchmark

Semantic Correlation Promoted Shape-Variant Context for Segmentation

Co-Occurrent Features in Semantic Segmentation

NTIRE 2019 Challenge on Image Enhancement: Methods and Results

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

Adaptive Pyramid Context Network for Semantic Segmentation

NTIRE 2019 Image Dehazing Challenge Report

High-Resolution Network for Photorealistic Style Transfer

CenterNet: Keypoint Triplets for Object Detection

High-Resolution Representations for Labeling Pixels and Regions

FCOS: Fully Convolutional One-Stage Object Detection

Deep High-Resolution Representation Learning for Human Pose Estimation

Hybrid Task Cascade for Instance Segmentation

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment

CCNet: Criss-Cross Attention for Semantic Segmentation

Rethinking ImageNet Pre-Training

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

Sequential Context Encoding for Duplicate Removal

Devil in the Details: Towards Accurate Single and Multiple Human Parsing

Dual Attention Network for Scene Segmentation

Context Refinement for Object Detection

Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation

A Deeply-Initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment

PSANet: Point-wise Spatial Attention Network for Scene Parsing

DetNet: Design Backbone for Object Detection

Parallel Feature Pyramid Network for Object Detection

Deeply Learned Compositional Models for Human Pose Estimation

OCNet: Object Context Network for Scene Parsing

Deep Feature Pyramid Reconfiguration for Object Detection

Quantized Densely Connected U-Nets for Efficient Landmark Localization

CornerNet: Detecting Objects as Paired Keypoints

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

Unified Perceptual Parsing for Scene Understanding

Macro-Micro Adversarial Network for Human Parsing

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network

Scale-Transferrable Object Detection

NU-Net: Deep Residual Wide Field of View Convolutional Neural Network for Semantic Segmentation

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks

Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

Direct Shape Regression Networks for End-to-End Face Alignment

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

Pyramid Attention Network for Semantic Segmentation

PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing

SNIPER: Efficient Multi-Scale Training

R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection

Learning a Discriminative Feature Network for Semantic Segmentation

Simple Baselines for Human Pose Estimation and Tracking

ExFuse: Enhancing Feature Fusion for Semantic Segmentation

Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark

Interleaved Structured Sparse Convolutional Neural Networks

Multi-scale Location-Aware Kernel Representation for Object Detection

Multi-Scale Structure-Aware Network for Human Pose Estimation

Adaptive Affinity Fields for Semantic Segmentation

Context Encoding for Semantic Segmentation

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

Dynamic-Structured Semantic Propagation Network

Style Aggregated Network for Facial Landmark Detection

Path Aggregation Network for Instance Segmentation

Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Deep Regionlets for Object Detection

Cascade R-CNN: Delving Into High Quality Object Detection

Single-Shot Object Detection with Enriched Semantics

Relation Networks for Object Detection