{"url":"/method/hrnet","slug":"hrnet","name":"HRNet","full_name":"HRNet","full_name_withheld":false,"description_markdown":"**HRNet**, or **High-Resolution Net**, is a general purpose convolutional neural network for tasks like semantic segmentation, object detection and image classification. It is able to maintain high resolution representations through the whole process. We start from a high-resolution [convolution](https://paperswithcode.com/method/convolution) stream, gradually add high-to-low resolution convolution streams one by one, and connect the multi-resolution streams in parallel. The resulting network consists of several ($4$ in the paper) stages and\r\nthe $n$th stage contains $n$ streams corresponding to $n$ resolutions. The authors conduct repeated multi-resolution fusions by exchanging the information across the parallel streams over and over.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deep High-Resolution Representation Learning for Visual Recognition","paper":"/paper/190807919","first_author":"Jingdong Wang","n_authors":12,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/190807919"},"source":{"url":"https://arxiv.org/abs/1908.07919v2","title":"Deep High-Resolution Representation Learning for Visual Recognition","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/HRNet/HRNet-Image-Classification/blob/8f158719e821836e21e6cba99a3241a12a13bc41/lib/models/cls_hrnet.py#L254","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutional Neural Networks","url":"/methods/category/convolutional-neural-networks","pwc_aliases":[]}],"n_papers_tagged":75,"archive_num_papers":75,"papers_newest_first":[{"paper":null,"title":"Joint angle model based learning to refine kinematic human pose estimation","date":"2025-07-15","arxiv_id":"2507.11075","n_code_links":0,"syntology":null},{"paper":null,"title":"Admissibility of Stein Shrinkage for Batch Normalization in the Presence of Adversarial Attacks","date":"2025-07-11","arxiv_id":"2507.08261","n_code_links":0,"syntology":null},{"paper":null,"title":"DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Measurement of Medial Elbow Joint Space using Landmark Detection","date":"2024-12-17","arxiv_id":"2412.13010","n_code_links":0,"syntology":null},{"paper":null,"title":"Sonicmesh: Enhancing 3D Human Mesh Reconstruction in Vision-Impaired Environments With Acoustic Signals","date":"2024-12-15","arxiv_id":"2412.11325","n_code_links":0,"syntology":null},{"paper":"/paper/hyperspectral-imaging-based-perception-in","title":"Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models","date":"2024-10-29","arxiv_id":"2410.22101","n_code_links":1,"syntology":null},{"paper":null,"title":"HRVMamba: High-Resolution Visual State Space Model for Dense Prediction","date":"2024-10-04","arxiv_id":"2410.03174","n_code_links":0,"syntology":null},{"paper":null,"title":"Convolutional Neural Networks for Predictive Modeling of Lung Disease","date":"2024-08-08","arxiv_id":"2408.12605","n_code_links":0,"syntology":null},{"paper":null,"title":"RHRSegNet: Relighting High-Resolution Night-Time Semantic Segmentation","date":"2024-07-08","arxiv_id":"2407.06016","n_code_links":0,"syntology":null},{"paper":null,"title":"Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods","date":"2024-06-25","arxiv_id":"2406.17382","n_code_links":0,"syntology":null},{"paper":"/paper/meshpose-unifying-densepose-and-3d-body-mesh-1","title":"MeshPose: Unifying DensePose and 3D Body Mesh reconstruction","date":"2024-06-14","arxiv_id":"2406.10180","n_code_links":1,"syntology":null},{"paper":null,"title":"Comparative Analysis of Hyperspectral Image Reconstruction Using Deep Learning for Agricultural and Biological Applications","date":"2024-05-22","arxiv_id":"2405.13331","n_code_links":0,"syntology":null},{"paper":null,"title":"Hyperspectral Image Reconstruction for Predicting Chick Embryo Mortality Towards Advancing Egg and Hatchery Industry","date":"2024-05-22","arxiv_id":"2405.13843","n_code_links":0,"syntology":null},{"paper":"/paper/hrnet-differentially-private-hierarchical-and","title":"HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization","date":"2024-05-13","arxiv_id":"2405.08043","n_code_links":1,"syntology":null},{"paper":null,"title":"Image segmentation of treated and untreated tumor spheroids by Fully Convolutional Networks","date":"2024-05-02","arxiv_id":"2405.01105","n_code_links":0,"syntology":null},{"paper":null,"title":"Gait Recognition from Highly Compressed Videos","date":"2024-04-18","arxiv_id":"2404.12183","n_code_links":0,"syntology":null},{"paper":null,"title":"Leveraging High-Resolution Features for Improved Deep Hashing-based Image Retrieval","date":"2024-03-20","arxiv_id":"2403.13747","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-baseline-for-efficient-hand-mesh","title":"A Simple Baseline for Efficient Hand Mesh Reconstruction","date":"2024-03-04","arxiv_id":"2403.01813","n_code_links":1,"syntology":{"ran":1,"of":15,"unverified":14,"pointer_only":0}},{"paper":null,"title":"Early Fusion of Features for Semantic Segmentation","date":"2024-02-08","arxiv_id":"2402.06091","n_code_links":0,"syntology":null},{"paper":null,"title":"Pose Estimation and Tracking for ASIST","date":"2023-11-30","arxiv_id":"2311.18665","n_code_links":0,"syntology":null},{"paper":"/paper/a-new-benchmark-and-model-for-challenging","title":"A New Benchmark and Model for Challenging Image Manipulation Detection","date":"2023-11-23","arxiv_id":"2311.14218","n_code_links":1,"syntology":null},{"paper":null,"title":"BiHRNet: A Binary high-resolution network for Human Pose Estimation","date":"2023-11-17","arxiv_id":"2311.10296","n_code_links":0,"syntology":null},{"paper":"/paper/an-easy-zero-shot-learning-combination","title":"An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategy","date":"2023-09-30","arxiv_id":"2310.00310","n_code_links":1,"syntology":null},{"paper":"/paper/deep-neighbor-layer-aggregation-for","title":"Deep Neighbor Layer Aggregation for Lightweight Self-Supervised Monocular Depth Estimation","date":"2023-09-17","arxiv_id":"2309.09272","n_code_links":1,"syntology":null},{"paper":"/paper/mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","arxiv_id":"2308.12817","n_code_links":1,"syntology":null},{"paper":null,"title":"SepHRNet: Generating High-Resolution Crop Maps from Remote Sensing imagery using HRNet with Separable Convolution","date":"2023-07-11","arxiv_id":"2307.05700","n_code_links":0,"syntology":null},{"paper":null,"title":"A region and category confidence-based multi-task network for carotid ultrasound image segmentation and classification","date":"2023-07-02","arxiv_id":"2307.00583","n_code_links":0,"syntology":null},{"paper":"/paper/xformer-fast-and-accurate-monocular-3d-body","title":"XFormer: Fast and Accurate Monocular 3D Body Capture","date":"2023-05-18","arxiv_id":"2305.11101","n_code_links":0,"syntology":null},{"paper":"/paper/visithers-visible-thermal-infrared-stereo","title":"VisiTherS: Visible-thermal infrared stereo disparity estimation of human silhouette","date":"2023-04-22","arxiv_id":"2304.11291","n_code_links":1,"syntology":null},{"paper":"/paper/ovenet-offset-vector-network-for-semantic","title":"OVeNet: Offset Vector Network for Semantic Segmentation","date":"2023-03-25","arxiv_id":"2303.14516","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/pose-estimation","name":"Pose Estimation","papers":28},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":26},{"task":"/task/segmentation","name":"Segmentation","papers":14},{"task":"/task/image-classification","name":"Image Classification","papers":6},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":6},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":6},{"task":"/task/2d-human-pose-estimation","name":"2D Human Pose Estimation","papers":5},{"task":"/task/decoder","name":"Decoder","papers":5},{"task":"/task/image-classification","name":"image-classification","papers":5},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":4},{"task":"/task/multi-person-pose-estimation","name":"Multi-Person Pose Estimation","papers":4},{"task":"/task/representation-learning","name":"Representation Learning","papers":4},{"task":"/task/3d-human-pose-estimation","name":"3D Human Pose Estimation","papers":3},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":3},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":3},{"task":"/task/2d-pose-estimation","name":"2D Pose Estimation","papers":2},{"task":"/task/3d-hand-pose-estimation","name":"3D Hand Pose Estimation","papers":2},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":2},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":2},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":2}],"tasks_shown":20,"n_tasks":101,"usage_by_year":[{"year":"2019","papers":3},{"year":"2020","papers":10},{"year":"2021","papers":17},{"year":"2022","papers":14},{"year":"2023","papers":12},{"year":"2024","papers":16},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/hrnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}