# HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet

arXiv: https://arxiv.org/abs/2112.10652 · HTML: https://mlsanity.com/paper/2112.10652/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 20 Dec 2021.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/1901.02985/) (2019)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://mlsanity.com/paper/1708.05344/) (2017)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Blockwisely Supervised Neural Architecture Search with Knowledge Distillation](https://mlsanity.com/paper/1911.13053/) (2019)
- [GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet](https://mlsanity.com/paper/2003.11236/) (2020)
- [HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation](https://mlsanity.com/paper/1804.02967/) (2018)
- [3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training](https://mlsanity.com/paper/1811.12506/) (2018)
- [C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/1912.09628/) (2019)
- [DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.15954/) (2021)
- [3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes](https://mlsanity.com/paper/1711.08580/) (2017)

## Built on by (most cited first, 14 of 14)

- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [One-Prompt to Segment All Medical Images](https://mlsanity.com/paper/2305.10300/) (2023)
- [SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass](https://mlsanity.com/paper/2602.06358/) (2026)
- [Vision Transformers in Medical Imaging: A Review](https://mlsanity.com/paper/2211.10043/) (2022)
- [InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning](https://mlsanity.com/paper/2308.15609/) (2023)
- [RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation](https://mlsanity.com/paper/2206.04682/) (2022)
- [Unsupervised Domain Adaptive Fundus Image Segmentation with Few Labeled Source Data](https://mlsanity.com/paper/2210.04379/) (2022)
- [OSTA: One-shot Task-adaptive Channel Selection for Semantic Segmentation of Multichannel Images](https://mlsanity.com/paper/2305.04766/) (2023)
- [Boundary-Aware Network for Abdominal Multi-Organ Segmentation](https://mlsanity.com/paper/2208.13774/) (2022)
- [Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation](https://mlsanity.com/paper/2405.03420/) (2024)
- [Boundary-Aware Network for Kidney Parsing](https://mlsanity.com/paper/2208.13338/) (2022)
- [Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks](https://mlsanity.com/paper/2309.16207/) (2023)
- [DMC-Net: Lightweight Dynamic Multi-Scale and Multi-Resolution Convolution Network for Pancreas Segmentation in CT Images](https://mlsanity.com/paper/2410.02129/) (2024)
- [Efficient Search of Implantable Adaptive Cells for Medical Image Segmentation](https://mlsanity.com/paper/2604.14849/) (2026)

## Abstract (arXiv)

Semantic segmentation of 3D medical images is a challenging task due to the high variability of the shape and pattern of objects (such as organs or tumors). Given the recent success of deep learning in medical image segmentation, Neural Architecture Search (NAS) has been introduced to find high-performance 3D segmentation network architectures. However, because of the massive computational requirements of 3D data and the discrete optimization nature of architecture search, previous NAS methods require a long search time or necessary continuous relaxation, and commonly lead to sub-optimal network architectures. While one-shot NAS can potentially address these disadvantages, its application in the segmentation domain has not been well studied in the expansive multi-scale multi-path search space. To enable one-shot NAS for medical image segmentation, our method, named HyperSegNAS, introduces a HyperNet to assist super-net training by incorporating architecture topology information. Such a HyperNet can be removed once the super-net is trained and introduces no overhead during architecture search. We show that HyperSegNAS yields better performing and more intuitive architectures compared to the previous state-of-the-art (SOTA) segmentation networks; furthermore, it can quickly and accurately find good architecture candidates under different computing constraints. Our method is evaluated on public datasets from the Medical Segmentation Decathlon (MSD) challenge, and achieves SOTA performances.