# HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection

arXiv: https://arxiv.org/abs/2412.06499 · HTML: https://mlsanity.com/paper/2412.06499/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Medical Transformer: Gated Axial-Attention for Medical Image Segmentation](https://mlsanity.com/paper/2102.10662/) (2021)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [BiFormer: Vision Transformer with Bi-Level Routing Attention](https://mlsanity.com/paper/2303.08810/) (2023)
- [UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2107.00781/) (2021)
- [Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization](https://mlsanity.com/paper/1908.00748/) (2019)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [Cephalometric Landmark Detection across Ages with Prototypical Network](https://mlsanity.com/paper/2406.12577/) (2024)
- [Attaining human-level performance with atlas location autocontext for anatomical landmark detection in 3D CT data](https://mlsanity.com/paper/1805.08687/) (2018)
- [DATR: Domain-adaptive transformer for multi-domain landmark detection](https://mlsanity.com/paper/2203.06433/) (2022)
- [CEPHA29: Automatic Cephalometric Landmark Detection Challenge 2023](https://mlsanity.com/paper/2212.04808/) (2022)
- [Revisiting Cephalometric Landmark Detection from the view of Human Pose Estimation with Lightweight Super-Resolution Head](https://mlsanity.com/paper/2309.17143/) (2023)
- [PELE scores: Pelvic X-ray Landmark Detection by Pelvis Extraction and Enhancement](https://mlsanity.com/paper/2305.04294/) (2023)
- [Feature Aggregation and Refinement Network for 2D AnatomicalLandmark Detection](https://mlsanity.com/paper/2111.00659/) (2021)

## Built on by (most cited first, 1 of 1)

- [Tracing Like a Clinician: Anatomy-Guided Spatial Priors for Cephalometric Landmark Detection](https://mlsanity.com/paper/2605.03358/) (2026)

## Abstract (arXiv)

Anatomical landmark detection (ALD) from a medical image is crucial for a wide array of clinical applications. While existing methods achieve quite some success in ALD, they often struggle to balance global context with computational efficiency, particularly with high-resolution images, thereby leading to the rise of a natural question: where is the performance limit of ALD? In this paper, we aim to forge performant ALD by proposing a bf HYbrid bf ATTention bf Network (HYATT-Net) with the following designs: (i) A novel hybrid architecture that integrates CNNs and Transformers. Its core is the BiFormer module, utilizing Bi-Level Routing Attention for efficient attention to relevant image regions. This, combined with Attention Residual Module(ARM), enables precise local feature refinement guided by the global context. (ii) A Feature Fusion Correction Module that aggregates multi-scale features and thus mitigates a resolution loss. Deep supervision with a mean-square error loss on multi-resolution heatmaps optimizes the model. Experiments on five diverse datasets demonstrate state-of-the-art performance, surpassing existing methods in accuracy, robustness, and efficiency. The HYATT-Net provides a promising solution for accurate and efficient ALD in complex medical images. Our codes and data are already released at: urlhttps://github.com/ECNUACRush/HYATT-Net.