# High-Resolution Representations for Labeling Pixels and Regions

arXiv: https://arxiv.org/abs/1904.04514 · HTML: https://mlsanity.com/paper/1904.04514/

## Key facts

- Cited by 211 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 30 of 211)

- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [SegViT: Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2210.05844/) (2022)
- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding](https://mlsanity.com/paper/2312.08733/) (2023)
- [Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features](https://mlsanity.com/paper/2104.04480/) (2021)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [The Lie Derivative for Measuring Learned Equivariance](https://mlsanity.com/paper/2210.02984/) (2022)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing](https://mlsanity.com/paper/2112.05144/) (2021)
- [Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures](https://mlsanity.com/paper/2404.03010/) (2024)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [StyleSwap: Style-Based Generator Empowers Robust Face Swapping](https://mlsanity.com/paper/2209.13514/) (2022)
- [Towards Online Domain Adaptive Object Detection](https://mlsanity.com/paper/2204.05289/) (2022)
- [Zoo-Tuning: Adaptive Transfer from a Zoo of Models](https://mlsanity.com/paper/2106.15434/) (2021)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [Generative Semantic Segmentation](https://mlsanity.com/paper/2303.11316/) (2023)
- [PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain](https://mlsanity.com/paper/2306.04557/) (2023)
- [Using DUCK-Net for Polyp Image Segmentation](https://mlsanity.com/paper/2311.02239/) (2023)
- [On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving](https://mlsanity.com/paper/2201.01850/) (2022)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)

## Abstract (arXiv)

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~citeSunXLW19, recently developed for human pose estimation, maintains high-resolution representations through the whole process by connecting high-to-low resolution convolutions in 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~citeSunXLW19. 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, 300W, 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 urlhttps://github.com/HRNet.