# SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

arXiv: https://arxiv.org/abs/2511.18493 · HTML: https://mlsanity.com/paper/2511.18493/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Placed in

- Mixture-of-experts / [Medical and biomedical MoE](https://mlsanity.com/moe/medical-and-biomedical-moe/)

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer](https://mlsanity.com/paper/2109.04335/) (2021)
- [Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining](https://mlsanity.com/paper/2402.03302/) (2024)
- [TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2107.05274/) (2021)
- [Multi-Task Dense Prediction via Mixture of Low-Rank Experts](https://mlsanity.com/paper/2403.17749/) (2024)
- [Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments](https://mlsanity.com/paper/1707.05733/) (2017)
- [Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts](https://mlsanity.com/paper/2405.13997/) (2024)
- [SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation](https://mlsanity.com/paper/2406.14896/) (2024)
- [EBHI-Seg: A Novel Enteroscope Biopsy Histopathological Haematoxylin and Eosin Image Dataset for Image Segmentation Tasks](https://mlsanity.com/paper/2212.00532/) (2022)
- [Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet](https://mlsanity.com/paper/2006.15954/) (2020)
- [EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices](https://mlsanity.com/paper/2410.15036/) (2024)
- [MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling](https://mlsanity.com/paper/2503.11144/) (2025)

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

- [φ-Balancing for Mixture-of-Experts Training](https://mlsanity.com/paper/2605.15403/) (2026)

## Abstract (arXiv)

The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static computation graphs with fixed routing. This leads to extra computation and makes it harder to adapt to changes in input. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures via a dual-path design with hierarchical gating and a Shape-Adapting Hub (SA-Hub) that harmonizes feature representations across convolutional and transformer modules. Embodied as SAGE with ConvNeXt and Vision Transformer UNet (SAGE-ConvNeXt+ViT-UNet), our model achieves a Dice score of 95.23% on EBHI, DSC scores of 92.78% and 91.42% on GlaS Test A and Test B, respectively, and 91.26% DSC at the WSI level on DigestPath, while exhibiting robust generalization under distribution shifts by adaptively balancing local refinement and global context. SAGE establishes a scalable foundation for dynamic expert routing in visual networks, thereby facilitating flexible visual reasoning. Project page: https://oxyzgiahuy.github.io/sage/